Young Researchers Symposium on Natural Language Processing 2016 (YRSNLP 2016)   General co-chairs  

2016   

情報処理学会   論文誌データベース（TOD）編集委員  

2015.4 - 2019.3   

NLP若手の会   共同運営委員長  

2015.1 - 2017.12   

Computational Intelligence   Editorial board  

2015.1 - 2017.12   

Transactions of the Association for Computational Linguistics   Standing reviewer team  

2014.11 - 2018.6   

人事院   国家公務員総合職試験工学区分（情報工学分科会）試験専門委員  

2014.9 - 2016.8   

情報処理学会   自然言語処理研究会 (NL) 幹事  

2014.4 - 2018.3   

放射線医学総合研究所   放射線影響・放射線防護に関する知見の収集・整理委員会委員  

2014.4 - 2016.3   

人工知能学会誌   論文誌編集委員  

2013.6 - 2017.5   

IJCNLP 2013   Workshop co-chairs  

2013   

言語処理学会   論文誌編集委員  

2012.10 - 2014.9   

情報処理学会東北支部   広報幹事  

2012.4 - 2014.3   

ACL 2012   Area co-chairs  

2012   

EMNLP-CoNLL 2012   Publication chair  

2012   

Improving Implicit Sentiments Analysis via Explanations of Multiple Perspectives Reviewed

An Wang, Huidong Jiang, Youmi Ma, Junfeng Jiang, Ao Liu, Naoaki Okazaki

IEEE Access   13   61136 - 61148   2025.4

Constructing Multimodal Datasets from Scratch for Rapid Development of a Japanese Visual Language Model Reviewed

Keito Sasagawa, Koki Maeda, Issa Sugiura, Shuhei Kurita, Naoaki Okazaki, Daisuke Kawahara

Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (System Demonstrations)   470 - 484   2025.4

訓練データを用いた言語モデル生成の確信度推定 Reviewed

吉川 和, 岡崎 直観

自然言語処理   32 ( 1 )   91 - 113   2025.3

Generative Data Augmentation for Aspect Sentiment Quad Prediction Reviewed

An Wang, Junfeng Jiang, Youmi Ma, Ao Liu, Naoaki Okazaki

Journal of Natural Language Processing   31 ( 4 )   1523 - 1544   2024.12

How You Prompt Matters! Even Task-Oriented Constraints in Instructions Affect LLM-Generated Text Detection Reviewed

Ryuto Koike, Masahiro Kaneko, Naoaki Okazaki

Findings of the Association for Computational Linguistics: EMNLP 2024   14384 - 14395   2024.11

Distributional Properties of Subword Regularization Reviewed

Marco Cognetta, Vilém Zouhar, Naoaki Okazaki

Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing   10753 - 10763   2024.11

Continual Pre-Training for Cross-Lingual LLM Adaptation: Enhancing Japanese Language Capabilities Reviewed

Kazuki Fujii, Taishi Nakamura, Mengsay Loem, Hiroki Iida, Masanari Ohi, Kakeru Hattori, Hirai Shota, Sakae Mizuki, Rio Yokota, Naoaki Okazaki

Proceedings of the First Conference on Language Modeling   (25 pages)   2024.10

SAIE Framework: Support Alone Isn't Enough - Advancing LLM Training with Adversarial Remarks Reviewed

Mengsay Loem, Masahiro Kaneko, Naoaki Okazaki

Proceedings of the 27th European Conference on Artificial Intelligence   3717 - 3724   2024.10

Building a Large Japanese Web Corpus for Large Language Models Reviewed

Naoaki Okazaki, Kakeru Hattori, Hirai Shota, Hiroki Iida, Masanari Ohi, Kazuki Fujii, Taishi Nakamura, Mengsay Loem, Rio Yokota, Sakae Mizuki

Proceedings of the First Conference on Language Modeling   (18 pages)   2024.10

SciCap+: A Knowledge Augmented Dataset to Study the Challenges of Scientific Figure Captioning Reviewed

Zhishen Yang, Raj Dabre, Hideki Tanaka, Naoaki Okazaki

Journal of Natural Language Processing   31 ( 3 )   1140 - 1165   2024.9

n-gram F-score for Evaluating Grammatical Error Correction Reviewed

Shota Koyama, Ryo Nagata, Hiroya Takamura, Naoaki Okazaki

Proceedings of the 17th International Natural Language Generation Conference   303 - 313   2024.9

Acceptability Evaluation of Naturally Written Sentences Reviewed

Vijay Daultani, Hector Vazquez Martinez, Naoaki Okazaki

Journal of Information Processing   32   652 - 666   2024.8

Likelihood-based Mitigation of Evaluation Bias in Large Language Models Reviewed

Masanari Ohi, Masahiro Kaneko, Ryuto Koike, Mengsay Loem, Naoaki Okazaki

Findings of the Association for Computational Linguistics ACL 2024   3237 - 3245   2024.8

An Analysis of BPE Vocabulary Trimming in Neural Machine Translation Reviewed

Marco Cognetta, Tatsuya Hiraoka, Rico Sennrich, Yuval Pinter, Naoaki Okazaki

Proceedings of the Fifth Workshop on Insights from Negative Results in NLP   48 - 50   2024.6

Building a Japanese Document-Level Relation Extraction Dataset Assisted by Cross-Lingual Transfer Reviewed

Youmi Ma, An Wang, Naoaki Okazaki

Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation   2567 - 2579   2024.5

Controlled Generation with Prompt Insertion for Natural Language Explanations in Grammatical Error Correction Reviewed

Masahiro Kaneko, Naoaki Okazaki

Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation   3955 - 3961   2024.5

Two Counterexamples to Tokenization and the Noiseless Channel Reviewed

Marco Cognetta, Vilém Zouhar, Sangwhan Moon, Naoaki Okazaki

Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation   16897 - 16906   2024.5

Evaluating Gender Bias of Pre-trained Language Models in Natural Language Inference by Considering All Labels Reviewed

Panatchakorn Anantaprayoon, Masahiro Kaneko, Naoaki Okazaki

Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation   6395 - 6408   2024.5

Solving NLP Problems through Human-System Collaboration: A Discussion-based Approach Reviewed

Masahiro Kaneko, Graham Neubig, Naoaki Okazaki

Findings of the Association for Computational Linguistics: EACL 2024   1644 - 1658   2024.3

文書レベル関係抽出における根拠認識の統合 Reviewed

Youmi Ma, An Wang, 岡崎 直観

自然言語処理   31 ( 1 )   105 - 133   2024.3

OUTFOX: LLM-generated Essay Detection through In-context Learning with Adversarially Generated Examples Reviewed

Ryuto Koike, Masahiro Kaneko, Naoaki Okazaki

The 38th Annual AAAI Conference on Artificial Intelligence   21258 - 21266   2024.2

Knowledge of Pretrained Language Models on Surface Information of Tokens.

Tatsuya Hiraoka, Naoaki Okazaki

CoRR   abs/2402.09808   2024

Causal Reasoning through Two Layers of Cognition for Improving Generalization in Visual Question Answering Reviewed

Trang Nguyen, Naoaki Okazaki

Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing   9221 - 9236   2023.12

Reducing Sequence Length by Predicting Edit Operations with Large Language Models Reviewed

Masahiro Kaneko, Naoaki Okazaki

Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing   10017 - 10029   2023.12

Improving Cross-Lingual Transfer for Open Information Extraction with Linguistic Feature Projection Reviewed

Youmi Ma, Bhushan Kotnis, Carolin Lawrance, Goran Glavaš, Naoaki Okazaki

Proceedings of the 3rd Workshop on Multi-lingual Representation Learning   125 - 138   2023.12

Query-based Image Captioning from Multi-context 360° Images Reviewed

Koki Maeda, Shuhei Kurita, Taiki Miyanishi, Naoaki Okazaki

Findings of the Association for Computational Linguistics: EMNLP 2023   6940 - 6954   2023.12

The Impact of Debiasing on the Performance of Language Models in Downstream Tasks is Underestimated Reviewed

Masahiro Kaneko, Danushka Bollegala, Naoaki Okazaki

Proceedings of the 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 2: Short Papers)   29 - 36   2023.11

Generative Data Augmentation for Aspect Sentiment Quad Prediction Reviewed

An Wang, Junfeng Jiang, Youmi Ma, Ao Liu, Naoaki Okazaki

Proceedings of the 12th Joint Conference on Lexical and Computational Semantics   128 - 140   2023.7

タスク指向対話システムにおけるユーザの特徴を考慮した話題導入 Reviewed

松原 真弓, 麻場 直喜, 内藤 昭一, 川村 晋太郎, 井口 慎也, 能勢 将樹, 岡崎 直観

情報処理学会論文誌デジタルプラクティス（DP）   4 ( 3 )   98 - 106   2023.7

Exploring Effectiveness of GPT-3 in Grammatical Error Correction: A Study on Performance and Controllability in Prompt-Based Methods Reviewed

Mengsay Loem, Masahiro Kaneko, Sho Takase, Naoaki Okazaki

Proceedings of the 18th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2023)   205 - 219   2023.7

ExtraPhrase: 生成型要約のための効率的データ拡張 Reviewed

Mengsay Loem, Sho Takase, Masahiro Kaneko, Naoaki Okazaki

自然言語処理   30 ( 2 )   489 - 506   2023.6

Parameter-Efficient Korean Character-Level Language Modeling Reviewed

Marco Cognetta, Sangwhan Moon, Lawrence Wolf-Sonkin, Naoaki Okazaki

Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume   2350 - 2356   2023.5

Semantic Specialization for Knowledge-based Word Sense Disambiguation Reviewed

Sakae Mizuki, Naoaki Okazaki

Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume   3457 - 3470   2023.5

DREEAM: Guiding Attention with Evidence for Improving Document-Level Relation Extraction Reviewed

Youmi Ma, An Wang, Naoaki Okazaki

Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume   1971 - 1983   2023.5

Selective-LAMA: Selective Prediction for Confidence-Aware Evaluation of Language Models Reviewed

Hiyori Yoshikawa, Naoaki Okazaki

Findings of the Association for Computational Linguistics: EACL 2023   2017 - 2028   2023.5

Comparing Intrinsic Gender Bias Evaluation Measures without using Human Annotated Examples Reviewed

Masahiro Kaneko, Danushka Bollegala, Naoaki Okazaki

Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume   2857 - 2863   2023.5

Nearest Neighbor Non-autoregressive Text Generation Reviewed

Ayana Niwa, Sho Takase, Naoaki Okazaki

Journal of Information Processing   31   334 - 352   2023.4

Improving Logical-Level Natural Language Generation with Topic-Conditioned Data Augmentation and Logical Form Generation Reviewed

Ao Liu, Congjian Luo, Naoaki Okazaki

Journal of Information Processing   31   332 - 343   2023.4

SciCap+: A Knowledge Augmented Dataset to Study the Challenges of Scientific Figure Captioning Reviewed

Zhishen Yang, Raj Dabre, Hideki Tanaka, Naoaki Okazaki

Proceedings of the Workshop on Scientific Document Understanding, co-located with 37th AAAI Conference on Artificial Intelligence   (Paper13)   2023.2

PLOG: Table-to-Logic Pretraining for Logical Table-to-Text Generation Reviewed

Ao Liu, Haoyu Dong, Naoaki Okazaki, Shi Han, Dongmei Zhang

Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing   5531 - 5546   2022.12

Gender Bias in Meta-Embeddings Reviewed

Masahiro Kaneko, Danushka Bollegala, Naoaki Okazaki

Findings of the Association for Computational Linguistics: EMNLP 2022   3118 - 3133   2022.12

マルチモーダル文書におけるテキストと画像の整合タスクの提案 Reviewed

村岡 雅康, 岡崎 直観, 小比田 涼介, 石井 悦子

自然言語処理   29 ( 4 )   1198 - 1232   2022.12

Unsupervised Domain Adaptation for Sparse Retrieval by Filling Vocabulary and Word Frequency Gaps Reviewed

Hiroki Iida, Naoaki Okazaki

Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)   752 - 765   2022.11

Improving Automatic Evaluation of Acceptability Based on Language Models with a Coarse Sentence Representation Reviewed

Vijay Daultani, Naoaki Okazaki

Proceedings of the 36th Pacific Asia Conference on Language, Information and Computation   109 - 118   2022.10

IMPARA: Impact based Metric for GEC using Parallel Data Reviewed

Koki Maeda, Masahiro Kaneko, Naoaki Okazaki

Proceedings of the 29th International Conference on Computational Linguistics   3578 - 3588   2022.10

Annotating Entity and Causal Relationships on Japanese Vehicle Recall Information Reviewed

Hsuan-Yu Kuo, Youmi Ma, Naoaki Okazaki

Proceedings of the 36th Pacific Asia Conference on Language, Information and Computation   783 - 791   2022.10

Zero-shotニューラル検索のための語彙一致と文脈の類似度による関連度スコアリング Reviewed

飯田 大貴, 岡崎 直観

情報処理学会論文誌データベース(TOD)   15 ( 3 )   20 - 35   2022.10

Debiasing Isn't Enough! – on the Effectiveness of Debiasing MLMs and Their Social Biases in Downstream Tasks Reviewed

Masahiro Kaneko, Danushka Bollegala, Naoaki Okazaki

Proceedings of the 29th International Conference on Computational Linguistics   1299 - 1310   2022.10

Gender Bias in Masked Language Models for Multiple Languages Reviewed

Masahiro Kaneko, Aizhan Imankulova, Danushka Bollegala, Naoaki Okazaki

Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies   2740 - 2750   2022.7

ExtraPhrase: Efficient Data Augmentation for Abstractive Summarization Reviewed

Mengsay Loem, Sho Takase, Masahiro Kaneko, Naoaki Okazaki

Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Student Research Workshop   16 - 24   2022.7

Learning How to Translate North Korean through South Korean Reviewed

Hwichan Kim, Sangwhan Moon, Naoaki Okazaki, Mamoru Komachi

Proceedings of the Thirteenth Language Resources and Evaluation Conference   6711 - 6718   2022.6

OpenKorPOS: Democratizing Korean Tokenization with Voting-Based Open Corpus Annotation Reviewed

Sangwhan Moon, Won Ik Cho, Hye Joo Han, Naoaki Okazaki, Nam Soo Kim

Proceedings of the Thirteenth Language Resources and Evaluation Conference   4975 - 4983   2022.6

多様な規則を活用した文法誤り訂正のデータ拡張に関する分析 Reviewed

古山 翔太, 高村 大也, 岡崎 直観

自然言語処理   29 ( 2 )   542 - 586   2022.6

Multi-Task Learning for Cross-Lingual Abstractive Summarization Reviewed

Sho Takase, Naoaki Okazaki

Proceedings of the Thirteenth Language Resources and Evaluation Conference   3008 - 3016   2022.6

Semi-Supervised Formality Style Transfer with Consistency Training Reviewed

Ao Liu, An Wang, Naoaki Okazaki

Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)   4689 - 4701   2022.5

Joint Entity and Relation Extraction Based on Table Labeling Using Convolutional Neural Networks Reviewed

Youmi Ma, Tatsuya Hiraoka, Naoaki Okazaki

Proceedings of the Sixth Workshop on Structured Prediction for NLP   11 - 21   2022.5

Why videos do not guide translations in video-guided machine translation? An empirical evaluation of video-guided machine translation dataset Reviewed

Zhishen Yang, Tosho Hirasawa, Mamoru Komachi, Naoaki Okazaki

Journal of Information Processing   30   388 - 396   2022.5

Word-level Perturbation Considering Word Length and Compositional Subwords Reviewed

Tatsuya Hiraoka, Sho Takase, Kei Uchiumi, Atsushi Keyaki, Naoaki Okazaki

Findings of the Association for Computational Linguistics: ACL 2022   3268 - 3275   2022.5

Single Model Ensemble for Subword Regularized Models in Low-Resource Machine Translation Reviewed

Sho Takase, Tatsuya Hiraoka, Naoaki Okazaki

Findings of the Association for Computational Linguistics: ACL 2022   2536 - 2541   2022.5

Interpretability for Language Learners Using Example-Based Grammatical Error Correction Reviewed

Masahiro Kaneko, Sho Takase, Ayana Niwa, Naoaki Okazaki

Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)   7176 - 7187   2022.5

単語分割と後段モデルの損失値を用いた同時最適化 Reviewed

平岡 達也, 高瀬 翔, 内海 慶, 欅 惇志, 岡崎 直観

自然言語処理   29 ( 1 )   112 - 143   2022.3

Recurrent Neural Hidden Markov Model for High-Order Transition Reviewed

Tatsuya Hiraoka, Sho Takase, Kei Uchiumi, Atsushi Keyaki, Naoaki Okazaki

ACM Transactions on Asian and Low-Resource Language Information Processing (TALLIP)   21 ( 2 )   1 - 15   2022.3

Named Entity Recognition and Relation Extraction Using Enhanced Table Filling by Contextualized Representations Reviewed

Youmi Ma, Tatsuya Hiraoka, Naoaki Okazaki

Journal of Natural Language Processing   29 ( 1 )   187 - 223   2022.3

Incorporating Semantic Textual Similarity and Lexical Matching for Information Retrieval Reviewed

Hiroki Iida, Naoaki Okazaki

Proceedings of the 35th Pacific Asia Conference on Language, Information and Computation   582 - 591   2021.11

Various Errors Improve Neural Grammatical Error Correction Reviewed

Shota Koyama, Hiroya Takamura, Naoaki Okazaki

Proceedings of the 35th Pacific Asia Conference on Language, Information and Computation   251 - 261   2021.11

Transformer-based Lexically Constrained Headline Generation Reviewed

Kosuke Yamada, Yuta Hitomi, Hideaki Tamori, Ryohei Sasano, Naoaki Okazaki, Kentaro Inui, Koichi Takeda

Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing   4085 - 4090   2021.11

Construction of a Corpus of Rhetorical Devices in Slogans and Structural Analysis of Antitheses Reviewed

Ayana Niwa, Naoaki Okazaki, Kohei Wakimoto, Keisuke Nishiguchi, Masataka Mouri

ACM Transactions on Asian and Low-Resource Language Information Processing (TALLIP)   20 ( 6 )   2021.11

Behavioral Testing of Knowledge Graph Embedding Models for Link Prediction Reviewed

Wiem Ben Rim, Carolin Lawrence, Kiril Gashteovski, Mathias Niepert, Naoaki Okazaki

Proceedings of the 3rd Conference on Automated Knowledge Base Construction   (19 pages)   2021.10

階層コード表現学習による上位下位関係の識別 Reviewed

水木 栄, 岡崎 直観

情報処理学会論文誌データベース(TOD)   14 ( 4 )   8 - 23   2021.10

Multimodal Pretraining Unmasked: {A Meta-Analysis and a Unified Framework of Vision-and-Language BERTs} Reviewed

Emanuele Bugliarello, Ryan Cotterell, Naoaki Okazaki, Desmond Elliott

Transactions of the Association for Computational Linguistics   9   978 - 994   2021.9

Predicting Antonyms in Context using BERT Reviewed

Ayana Niwa, Keisuke Nishiguchi, Naoaki Okazaki

Proceedings of the 14th International Conference on Natural Language Generation   48 - 54   2021.8

Field Experiments of Real Time Foreign News Distribution Powered by MT Reviewed

Keiji Yasuda, Ichiro Yamada, Naoaki Okazaki, Hideki Tanaka, Hidehiro Asaka, Takeshi Anzai, Fumiaki Sugaya

Proceedings of Machine Translation Summit XVIII: Users and Providers Track   227 - 232   2021.8

Joint Optimization of Tokenization and Downstream Model Reviewed

Tatsuya Hiraoka, Sho Takase, Kei Uchiumi, Atsushi Keyaki, Naoaki Okazaki

Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021   244 - 255   2021.8

The Effects and Mitigation of Out-of-Vocabulary in Universal Language Models Reviewed

Sangwhan Moon, Naoaki Okazaki

Journal of Information Processing   29   490 - 503   2021.7

テキストベクトルの重みづけを用いたタスクに対する単語分割の最適化 Reviewed

平岡 達也, 高瀬 翔, 内海 慶, 欅 惇志, 岡崎 直観

自然言語処理   28 ( 2 )   479 - 507   2021.6

SWAGex at SemEval-2020 Task 4: Commonsense Explanation as Next Event Prediction Reviewed

Wiem Ben Rim, Naoaki Okazaki

Proceedings of the Fourteenth Workshop on Semantic Evaluation   422 - 429   2020.12

Multi-dialect Neural Machine Translation for 48 Low-resource Japanese Dialects Reviewed

Kaori Abe, Yuichiroh Matsubayashi, Naoaki Okazaki, Kentaro Inui

Journal of Natural Language Processing   27 ( 4 )   781 - 800   2020.12

Image Caption Generation for News Articles Reviewed

Zhishen Yang, Naoaki Okazaki

Proceedings of the 28th International Conference on Computational Linguistics   1941 - 1951   2020.12

TextLearner at SemEval-2020 Task 10: A Contextualized Ranking System in Solving Emphasis Selection in Text Reviewed

Zhishen Yang, Lars Wolfsteller, Naoaki Okazaki

Proceedings of the Fourteenth Workshop on Semantic Evaluation   1691 - 1697   2020.12

You May Like This Hotel Because ...: Identifying Evidence for Explainable Recommendations Reviewed

Shin Kanouchi, Masato Neishi, Yuta Hayashibe, Hiroki Ouchi, Naoaki Okazaki

Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing   890 - 899   2020.12

PatchBERT: Just-in-Time, Out-of-Vocabulary Patching Reviewed

Sangwhan Moon, Naoaki Okazaki

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)   7846 - 7852   2020.11

Optimizing Word Segmentation for Downstream Task Reviewed

Tatsuya Hiraoka, Sho Takase, Kei Uchiumi, Atsushi Keyaki, Naoaki Okazaki

Findings of the Association for Computational Linguistics: EMNLP 2020   1341 - 1351   2020.11

Learning to Select, Track, and Generate for Data-to-Text Reviewed

Hayate Iso, Yui Uehara, Tatsuya Ishigaki, Hiroshi Noji, Eiji Aramaki, Ichiro Kobayashi, Yusuke Miyao, Naoaki Okazaki, Hiroya Takamura

Journal of Natural Language Processing   27 ( 3 )   599 - 626   2020.9

Improving Truthfulness of Headline Generation Reviewed

Kazuki Matsumaru, Sho Takase, Naoaki Okazaki

Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics   1335 - 1346   2020.7

Enhancing Machine Translation with Dependency-Aware Self-Attention Reviewed

Emanuele Bugliarello, Naoaki Okazaki

Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics   1618 - 1627   2020.7

It's Easier to Translate out of English than into it: Measuring Neural Translation Difficulty by Cross-Mutual Information Reviewed

Emanuele Bugliarello, Sabrina J. Mielke, Antonios Anastasopoulos, Ryan Cotterell, Naoaki Okazaki

Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics   1640 - 1649   2020.7

Empirical Exploration of the Challenges in Temporal Relation Extraction from Clinical Text Reviewed

Diana Galvan-Sosa, Koji Matsuda, Naoaki Okazaki, Kentaro Inui

Journal of Natural Language Processing   27 ( 2 )   383 - 409   2020.6

Evaluation Dataset for Zero Pronoun in Japanese to English Translation Reviewed

Sho Shimazu, Sho Takase, Toshiaki Nakazawa, Naoaki Okazaki

Proceedings of the 12th Language Resources and Evaluation Conference   3630 - 3634   2020.5

Jamo Pair Encoding: Subcharacter Representation-based Extreme Korean Vocabulary Compression for Efficient Subword Tokenization Reviewed

Sangwhan Moon, Naoaki Okazaki

Proceedings of the 12th Language Resources and Evaluation Conference   3490 - 3497   2020.5

Analyzing the Variation Property of Contextualized Word Representations Reviewed

Sakae Mizuki, Naoaki Okazaki

AI 2019: Advances in Artificial Intelligence   393 - 405   2019.12

Neural Question Generation using Interrogative Phrases Reviewed

Yuichi Sasazawa, Sho Takase, Naoaki Okazaki

Proceedings of the 12th International Conference on Natural Language Generation   106 - 111   2019.10

Stance Detection Attending External Knowledge from Wikipedia Reviewed

Kazuaki Hanawa, Akira Sasaki, Naoaki Okazaki, Kentaro Inui

Journal of Information Processing   27   499 - 506   2019.8

Learning to Select, Track, and Generate for Data-to-Text Reviewed

Hayate Iso, Yui Uehara, Tatsuya Ishigaki, Hiroshi Noji, Eiji Aramaki, Ichiro Kobayashi, Yusuke Miyao, Naoaki Okazaki, Hiroya Takamura

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics   2102 - 2113   2019.7

TokyoTech_NLP at SemEval-2019 Task 3: Emotion-related Symbols in Emotion Detection Reviewed

Zhishen Yang, Sam Vijlbrief, Naoaki Okazaki

Proceedings of the 13th International Workshop on Semantic Evaluation   350 - 354   2019.6

Positional Encoding to Control Output Sequence Length Reviewed

Sho Takase, Naoaki Okazaki

Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)   3999 - 4004   2019.6

Multi-dialect Neural Machine Translation and Dialectometry Reviewed

Kaori Abe, Yuichiroh Matsubayashi, Naoaki Okazaki, Kentaro Inui

Proceedings of the 32nd Pacific Asia Conference on Language, Information and Computation   2018.12

Reducing Odd Generation from Neural Headline Generation Reviewed

Shun Kiyono, Sho Takase, Jun Suzuki, Naoaki Okazaki, Kentaro Inui, Masaaki Nagata

Proceedings of the 32nd Pacific Asia Conference on Language, Information and Computation   2018.12

Unsupervised Token-wise Alignment to Improve Interpretation of Encoder-Decoder Models Reviewed

Shun Kiyono, Sho Takase, Jun Suzuki, Naoaki Okazaki, Kentaro Inui, Masaaki Nagata

Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP   74 - 81   2018.11

Investigating the Challenges of Temporal Relation Extraction from Clinical Text Reviewed

Diana Galvan, Naoaki Okazaki, Koji Matsuda, Kentaro Inui

Proceedings of the Ninth International Workshop on Health Text Mining and Information Analysis   55 - 64   2018.10

Predicting Stances from Social Media Posts using Factorization Machines Reviewed

Akira Sasaki, Kazuaki Hanawa, Naoaki Okazaki, Kentaro Inui

Proceedings of the 27th International Conference on Computational Linguistics   3381 - 3390   2018.8

A Joint Neural Model for Fine-Grained Named Entity Classification of Wikipedia Articles Reviewed

Masatoshi Suzuki, Koji Matsuda, Satoshi Sekine, Naoaki Okazaki, Kentaro Inui

IEICE Transactions on Information and Systems, Special Section on Semantic Web and Linked Data   E101.D ( 1 )   73 - 81   2018.1

A Crowdsourcing Approach for Annotating Causal Relation Instances in Wikipedia Reviewed

Kazuaki Hanawa, Akira Sasaki, Naoaki Okazaki, Kentaro Inui

Proceedings of the 31st Pacific Asia Conference on Language, Information and Computation   336 - 345   2017.11

Proofread Sentence Generation as Multi-Task Learning with Editing Operation Prediction Reviewed

Yuta Hitomi, Hideaki Tamori, Naoaki Okazaki, Kentaro Inui

Proceedings of the Eighth International Joint Conference on Natural Language Processing   436 - 441   2017.11

A Neural Language Model for Dynamically Representing the Meanings of Unknown Words and Entities in a Discourse Reviewed

Sosuke Kobayashi, Naoaki Okazaki, Kentaro Inui

Proceedings of the Eighth International Joint Conference on Natural Language Processing   473 - 483   2017.11

Analyzing the Revision Logs of a Japanese Newspaper for Article Quality Assessment Reviewed

Hideaki Tamori, Yuta Hitomi, Naoaki Okazaki, Kentaro Inui

Proceedings of the 2017 EMNLP Workshop: Natural Language Processing meets Journalism   46 - 50   2017.9

Learning Co-Substructures by Kernel Dependence Maximization Reviewed

Sho Yokoi, Daichi Mochihashi, Ryo Takahashi, Naoaki Okazaki, Kentaro Inui

Proceedings of the 26th International Joint Conference on Artificial Intelligence   3329 - 3335   2017.8

関係パタンの分散表現の計算 Reviewed

高瀬 翔, 岡崎 直観, 乾 健太郎

人工知能学会論文誌   32 ( 4 )   D-G96_1-11   2017.7

Other Topics You May Also Agree or Disagree: Modeling Inter-Topic Preferences using Tweets and Matrix Factorization Reviewed

Akira Sasaki, Kazuaki Hanawa, Naoaki Okazaki, Kentaro Inui

Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)   398 - 408   2017.7

The mechanism of additive composition Reviewed

Ran Tian, Naoaki Okazaki, Kentaro Inui

Machine Learning   106 ( 7 )   1083 - 1130   2017.7

Supervised Approaches for Japanese Wikification Reviewed

Shuangshuang Zhou, Naoaki Okazaki, Koji Matsuda, Ran Tian, Kentaro Inui

Journal of Information Processing   25   341 - 350   2017.4

Handling Multiword Expressions in Causality Estimation Reviewed

Shota Sasaki, Sho Takase, Naoya Inoue, Naoaki Okazaki, Kentaro Inui

IWCS 2017 — 12th International Conference on Computational Semantics — Short papers   (6 pages)   2017

A Corpus of Deep Argumentative Structures as an Explanation to Argumentative Relations. Reviewed

Paul Reisert, Naoya Inoue, Naoaki Okazaki, Kentaro Inui

CoRR   abs/1712.02480   2017

Modeling Context-sensitive Selectional Preference with Distributed Representations Reviewed

Naoya Inoue, Yuichiroh Matsubayashi, Masayuki Ono, Naoaki Okazaki, Kentaro Inui

Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers   2829 - 2838   2016.12

Modeling Discourse Segments in Lyrics Using Repeated Patterns Reviewed

Kento Watanabe, Yuichiroh Matsubayashi, Naho Orita, Naoaki Okazaki, Kentaro Inui, Satoru Fukayama, Tomoyasu Nakano, Jordan Smith, Masataka Goto

Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers   1959 - 1969   2016.12

Generating Video Description using Sequence-to-sequence Model with Temporal Attention Reviewed

Natsuda Laokulrat, Sang Phan, Noriki Nishida, Raphael Shu, Yo Ehara, Naoaki Okazaki, Yusuke Miyao, Hideki Nakayama

Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers   44 - 52   2016.12

Neural Headline Generation on Abstract Meaning Representation Reviewed

Sho Takase, Jun Suzuki, Naoaki Okazaki, Tsutomu Hirao, Masaaki Nagata

Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing   1054 - 1059   2016.11

Neural Joint Learning for Classifying Wikipedia Articles into Fine-grained Named Entity Types Reviewed

Masatoshi Suzuki, Koji Matsuda, Satoshi Sekine, Naoaki Okazaki, Kentaro Inui

Proceedings of the 30th Pacific Asia Conference on Language, Information and Computation: Posters   535 - 544   2016.10

A Pipeline Japanese Entity Linking System with Embedding Features Reviewed

Shuangshuang Zhou

Proceedings of the 30th Pacific Asia Conference on Language, Information and Computation: Oral Papers   267 - 276   2016.10

Toward the automatic extraction of knowledge of usable goods Reviewed

Mei Uemura, Naho Orita, Naoaki Okazaki, Kentaro Inui

Proceedings of the 30th Pacific Asia Conference on Language, Information and Computation: Oral Papers   277 - 285   2016.10

Recognizing Open-Vocabulary Relations between Objects in Images Reviewed

Masayasu Muraoka, Sumit Maharjan, Masaki Saito, Kota Yamaguchi, Naoaki Okazaki, Takayuki Okatani, Kentaro Inui

Proceedings of the 30th Pacific Asia Conference on Language, Information and Computation: Oral Papers   239 - 248   2016.10

Building a Corpus for Japanese Wikification with Fine-Grained Entity Classes Reviewed

Davaajav Jargalsaikhan, Naoaki Okazaki, Koji Matsuda, Kentaro Inui

Proceedings of the ACL 2016 Student Research Workshop   138 - 144   2016.8

Learning Semantically and Additively Compositional Distributional Representations Reviewed

Ran Tian, Naoaki Okazaki, Kentaro Inui

Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)   1277 - 1287   2016.8

Composing Distributed Representations of Relational Patterns Reviewed

Sho Takase, Naoaki Okazaki, Kentaro Inui

Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)   2276 - 2286   2016.8

Dynamic Entity Representation with Max-pooling Improves Machine Reading Reviewed

Sosuke Kobayashi, Ran Tian, Naoaki Okazaki, Kentaro Inui

Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies   850 - 855   2016.6

Modeling semantic compositionality of relational patterns Reviewed

Sho Takase, Naoaki Okazaki, Kentaro Inui

Engineering Applications of Artificial Intelligence   50   256 - 264   2016.4

Fine-Grained Named Entity Classification with Wikipedia Article Vectors Reviewed

Masatoshi Suzuki, Koji Matsuda, Satoshi Sekine, Naoaki Okazaki, Kentaro Inui

2016 IEEE/WIC/ACM International Conference on Web Intelligence (WI)   483 - 486   2016

Learning to Describe E-Commerce Images from Noisy Online Data Reviewed

Takuya Yashima, Naoaki Okazaki, Kentaro Inui, Kota Yamaguchi, Takayuki Okatani

Proceedings of the Asian Conference on Computer Vision   85 - 100   2016

Stance Classification by Recognizing Related Events about Targets Reviewed

Akira Sasaki, Junta Mizuno, Naoaki Okazaki, Kentaro Inui

2016 IEEE/WIC/ACM International Conference on Web Intelligence (WI)   582 - 587   2016

Web情報からの罹患検出を対象とした事実性解析・主体解析の誤り分析 Reviewed

叶内 晨, 北川 善彬, 荒牧 英治, 岡崎直観, 小町 守

自然言語処理   22 ( 5 )   363 - 396   2015.12

Reducing Lexical Features in Parsing by Word Embeddings Reviewed

Hiroya Komatsu, Ran Tian, Naoaki Okazaki, Kentaro Inui

Proceedings of the 29th Pacific Asia Conference on Language, Information and Computation (PACLIC 29)   106 - 113   2015.10

Fast and Large-scale Unsupervised Relation Extraction Reviewed

Sho Takase, Naoaki Okazaki, Kentaro Inui

Proceedings of the 29th Pacific Asia Conference on Language, Information and Computation (PACLIC 29)   96 - 105   2015.10

Disease Event Detection based on Deep Modality Analysis Reviewed

Yoshiaki Kitagawa, Mamoru Komachi, Eiji Aramaki, Naoaki Okazaki, Hiroshi Ishikawa

Proceedings of the ACL-IJCNLP 2015 Student Research Workshop   28 - 34   2015.7

Who caught a cold ? - Identifying the subject of a symptom Reviewed

Shin Kanouchi, Mamoru Komachi, Naoaki Okazaki, Eiji Aramaki, Hiroshi Ishikawa

Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)   1660 - 1670   2015.7

A Computational Approach for Generating Toulmin Model Argumentation Reviewed

Paul Reisert, Naoya Inoue, Naoaki Okazaki, Kentaro Inui

Proceedings of the 2nd Workshop on Argumentation Mining   45 - 55   2015.6

Annotating Geographical Entities on Microblog Text Reviewed

Koji Matsuda, Akira Sasaki, Naoaki Okazaki, Kentaro Inui

Proceedings of The 9th Linguistic Annotation Workshop   85 - 94   2015.6

東日本大震災後に日本栄養士会から派遣された災害支援管理栄養士・栄養士の支援活動に関する分析 Reviewed

伊藤 聖來, 須藤 紀子, 笠岡(坪山) 宣代, 岡崎 直観, 鍋島 啓太, 金谷 泰宏, 奥村 貴史, 下浦 佳之

日本栄養士会雑誌   58 ( 2 )   33 - 42   2015.2

Finding The Best Model Among Representative Compositional Models Reviewed

Masayasu Muraoka, Sonse Shimaoka, Kazeto Yamamoto, Yotaro Watanabe, Naoaki Okazaki, Kentaro Inui

Proceedings of the 28th Pacific Asia Conference on Language, Information and Computation (PACLIC 28)   65 - 74   2014.12

Exploring Linguistic Features for Named Entity Disambiguation Reviewed

Shuangshuang Zhou, Canasai Kruengkrai, Naoaki Okazaki, Kentaro Inui

International Journal of Computational Linguistics and Applications   5 ( 2 )   49 - 66   2014.12

A Corpus Study for Identifying Evidence on Microblogs Reviewed

Paul Reisert, Junta Mizuno, Miwa Kanno, Naoaki Okazaki, Kentaro Inui

Proceedings of the 8th Linguistic Annotation Workshop (LAW VIII 2014)   70 - 74   2014.8

Mining False Information on Twitter for a Major Disaster Situation Reviewed

Keita Nabeshima, Junta Mizuno, Naoaki Okazaki, Kentaro Inui

Proceedings of the 2014 International Conference on Active Media Technology (AMT2014)   96 - 109   2014.8

Extracting and Aggregating False Information from Microblogs Reviewed

Naoaki Okazaki, Keita Nabeshima, Kento Watanabe, Junta Mizuno, Kentaro Inui

Proceedings of the Workshop on Language Processing and Crisis Information 2013   36 - 43   2013.10

Is a 204 cm Man Tall or Small? Acquisition of Numerical Common Sense from the Web Reviewed

Katsuma Narisawa, Yotaro Watanabe, Junta Mizuno, Naoaki Okazaki, Kentaro Inui

Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)   382 - 391   2013.8

Detecting Chronic Critics Based on Sentiment Polarity and User's Behavior in Social Media Reviewed

Sho Takase, Akiko Murakami, Miki Enoki, Naoaki Okazaki, Kentaro Inui

51st Annual Meeting of the Association for Computational Linguistics Proceedings of the Student Research Workshop   110 - 116   2013.8

Named entity recognition with multiple segment representations Reviewed

Han-Cheol Cho, Naoaki Okazaki, Makoto Miwa, Jun'ichi Tsujii

Information Processing & Management   49 ( 4 )   954 - 965   2013.7

返信・非公式リツイートに基づくツイート空間の論述構造解析 Reviewed

大和田裕亮, 水野淳太, 岡崎直観, 乾健太郎, 石塚満

自然言語処理   20 ( 3 )   423 - 459   2013.6

訂正パターンに基づく誤情報の収集と拡散状況の分析 Reviewed

鍋島啓太, 渡邉研斗, 水野淳太, 岡崎直観, 乾健太郎

自然言語処理   20 ( 3 )   461 - 484   2013.6

カテゴリ間の兄弟関係を活用した集合拡張 Reviewed

高瀬翔, 岡崎直観, 乾健太郎

自然言語処理   20 ( 2 )   273 - 296   2013.6

Learning Abbreviations from Chinese and English Terms by Modeling Non-local Information Reviewed

Xu Sun, Naoaki Okazaki, Junichi Tsujii, Houfeng Wang

ACM Transactions on Asian Language Information Processing   12 ( 2 )   5:1 - 5:17   2013.6

Inducing Context Gazetteers from Encyclopedic Database for Named Entity Recognition Reviewed

Han-Cheol Cho, Naoaki Okazaki, Kentaro Inui

Proceedings of the 17th Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD 2013)   378 - 389   2013.4

Evidence in Automatic Error Correction Improves Learners’ English Skill Reviewed

Jiro Umezawa, Junta Mizuno, Naoaki Okazaki, Kentaro Inui

Proceedings of the 14th International Conference on Intelligent Text Processing and Computational Linguistics (CICLing 2013)   559 - 571   2013.3

Discriminative Learning of First-order Weighted Abduction from Partial Discourse Explanations Reviewed

Kazeto Yamamoto, Naoya Inoue, Yotaro Watanabe, Naoaki Okazaki, Kentaro Inui

Proceedings of the 14th International Conference on Intelligent Text Processing and Computational Linguistics (CICLing 2013)   545 - 558   2013.3

A preference learning approach to sentence ordering for multi-document summarization Reviewed

Danushka Bollegala, Naoaki Okazaki, Mitsuru Ishizuka

Information Sciences   217   78 - 95   2012.12

Acquiring and Generalizing Causal Inference Rules from Deverbal Noun Constructions Reviewed

Shohei Tanaka, Naoaki Okazaki, Mitsuru Ishizuka

Proceedings of the 24th International Conference on Computational Linguistics (COLING 2012): Posters   1209 - 1218   2012.12

A Latent Discriminative Model for Compositional Entailment Relation Recognition Using Natural Logic Reviewed

Yotaro Watanabe, Junta Mizuno, Eric Nichols, Naoaki Okazaki, Kentaro Inui

Proceedings of the 24th International Conference on Computational Linguistics (COLING 2012)   2805 - 2820   2012.12

Leveraging Diverse Lexical Resources for Textual Entailment Recognition Reviewed

Yotaro Watanabe, Junta Mizuno, Eric Nichols, Katsuma Narisawa, Keita Nabeshima, Naoaki Okazaki, Kentaro Inui

ACM Transactions on Asian Language Information Processing   11 ( 4 )   18:1 - 18:22   2012.12

Set Expansion using Sibling Relations between Semantic Categories Reviewed

Sho Takase, Naoaki Okazaki, Kentaro Inui

Proceedings of the 26th Pacific Asia Conference on Language, Information and Computation (PACLIC 26)   525 - 534   2012.11

BioCreative III interactive task: an overview Reviewed

Cecilia N Arighi, Phoebe M Roberts, Shashank Agarwal, Sanmitra Bhattacharya, Gianni Cesareni, Andrew Chatr-aryamontri, Simon Clematide, Pascale Gaudet, Michelle Gwinn Giglio, Ian Harrow, Eva Huala, Martin Krallinger, Ulf Leser, Donghui Li, Feifan Liu, Zhiyong Lu, Lois J Maltais, Naoaki Okazaki, Livia Perfetto, Fabio Rinaldi, Rune Sætre, David Salgado, Padmini Srinivasan, Philippe E Thomas, Luca Toldo, Lynette Hirschman, Cathy H Wu

BMC Bioinformatics   12 ( Suppl 8 )   S8   2011.9

The gene normalization task in BioCreative III Reviewed

Zhiyong Lu, Hung-Yu Kao, Chih-Hsuan Wei, Minlie Huang, Jingchen Liu, Cheng-Ju Kuo, Chun-Nan Hsu, Richard Tzong-Han Tsai, Hong-Jie Dai, Naoaki Okazaki, Han-Cheol Cho, Martin Gerner, Illes Solt, Shashank Agarwal, Feifan Liu, Dina Vishnyakova, Patrick Ruch, Martin Romacker, Fabio Rinaldi, Sanmitra Bhattacharya, Padmini Srinivasan, Hongfang Liu, Manabu Torii, Sergio Matos, David Campos, Karin Verspoor, Kevin M. Livingston, John W. Wilbur

BMC Bioinformatics   12 ( Suppl 8 )   S9   2011.9

Fast Newton-CG Method for Batch Learning of Conditional Random Fields Reviewed

Yuta Tsuboi, Yuya Unno, Hisashi Kashima, Naoaki Okazaki

Proceedings of the Twenty-Fifth Conference on Artificial Intelligence (AAAI-11)   489 - 494   2011.8

Automatic Acquisition of Huge Training Data for Bio-Medical Named Entity Recognition Reviewed

Yu Usami, Han-Cheol Cho, Naoaki Okazaki, Jun'ichi Tsujii

Proceedings of BioNLP 2011 Workshop   65 - 73   2011.6

集合間類似度に対する簡潔かつ高速な類似文字列検索アルゴリズム Reviewed

岡崎直観, 辻井潤一

自然言語処理   18 ( 2 )   89 - 118   2011.6

Wikipediaを教師データに用いた要約文書収集クエリパターンの学習 Reviewed

田中翔平, 岡崎直観, 石塚 満

人工知能学会論文誌   26 ( 2 )   366 - 375   2011.3

Medie and Info-pubmed: 2010 update Reviewed

Tomoko Ohta, Takuya Matsuzaki, Naoaki Okazaki, Makoto Miwa, Rune Sætre, Sampo Pyysalo, Jun'ichi Tsujii

BMC Bioinformatics   11 ( Suppl 5 )   P7   2010.10

The gene normalization and intractive systems of the University of Tokyo in the BioCreative III challenge Reviewed

Naoaki Okazaki, Han-Cheol Cho, Rune Sætre, Sampo Pyysalo, Tomoko Ohta, Jun'ichi Tsujii

Proceedings of BioCreative III   125 - 130   2010.9

Simple and Efficient Algorithm for Approximate Dictionary Matching Reviewed

Naoaki Okazaki, Jun'ichi Tsujii

Proceedings of the 23rd International Conference on Computational Linguistics (COLING 2010)   851 - 859   2010.8

Learning Web Query Patterns for Imitating Wikipedia Articles Reviewed

Shouhei Tanaka, Naoaki Okazaki, Mitsuru Ishizuka

Proceedings of the 23rd International Conference on Computational Linguistics (COLING 2010): Posters   1229 - 1237   2010.8

自動意味役割付与における意味役割の汎化 Reviewed

松林優一郎, 岡崎直観, 辻井潤一

自然言語処理   17 ( 4 )   59 - 89   2010.7

Building a High Quality Sense Inventory for Improved Abbreviation Disambiguation Reviewed

Naoaki Okazaki, Sophia Ananiadou, Jun'ichi Tsujii

Bioinformatics   26 ( 9 )   1246 - 1253   2010.5

A bottom-up approach to sentence ordering for multi-document summarization Reviewed

Danushka Bollegala, Naoaki Okazaki, Mitsuru Ishizuka

Information Processing & Management   46 ( 1 )   89 - 109   2010.1

Opinion Classification with Tree Kernel SVM Using Linguistic Modality Analysis Reviewed

Takeshi Kobayakawa, Tadashi Kumano, Hideki Tanaka, Naoaki Okazaki, Jin-Dong Kim, Junichi Tsujii

Proceedings of the 18th ACM Conference on Information and Knowledge Management (CIKM 2009)   1791 - 1794   2009.11

Supporting Systematic Reviews using Text Mining Reviewed

Sophia Ananiadou, Brian Rea, Naoaki Okazaki, Rob Proctor, James Thomas

Social Science Computer Review   27 ( 4 )   509 - 523   2009.11

Accurate and Robust Semantic Role Labeling with Multiple Generalization Criteria in PropBank Reviewed

Yuichiroh Matsubayashi, Naoaki Okazaki, Jun'ichi Tsujii

Proceedings of the 5th International Conference on Generative Approaches to the Lexicon (GL 2009)   97 - 104   2009.9

Community Platform for Pathway Model Building Reviewed

Yukiko Matsuoka, Samik Ghosh, Norihiko Kikuchi, Rune Saetre, Brian Kemper, Naoaki Okazaki, Sophia Ananiadou, Jun'ichi Tsujii, Hiroaki Kitano

Proceedings of the 10th International Conference on Systems Biology (ICSB 2009)   139 - 140   2009.9

Robust Approach to Abbreviating Terms: A Discriminative Latent Variable Model with Global Information Reviewed

Xu Sun, Naoaki Okazaki, Jun'ichi Tsujii

Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP (ACL-IJCNLP 2009)   905 - 913   2009.8

Unsupervised Relation Extraction by Mining Wikipedia Texts Using Information from the Web Reviewed

Yulan Yan, Naoaki Okazaki, Yutaka Matsuo, Zhenglu Yang, Mitsuru Ishizuka

Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP (ACL-IJCNLP 2009)   1021 - 1029   2009.8

A Comparative Study on Generalization of Semantic Roles in FrameNet Reviewed

Yuichiroh Matsubayashi, Naoaki Okazaki, Jun'ichi Tsujii

Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP (ACL-IJCNLP 2009)   19 - 27   2009.8

Semi-Supervised Lexicon Mining from Parenthetical Expressions in Monolingual Web Pages Reviewed

Xianchao Wu, Naoaki Okazaki, Jun'ichi Tsujii

Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL/HLT 2009)   424 - 432   2009.6

A Chinese-Japanese Lexical Machine Translation through a Pivot Language Reviewed

Takashi Tsunakawa, Naoaki Okazaki, Xiao Liu, Jun'ichi Tsujii

ACM Transactions on Asian Language Information Processing (TALIP)   8 ( 2 )   9:1 - 9:21   2009.5

Improving English-to-Chinese Translation for Technical Terms Using Morphological Information Reviewed

Xianchao Wu, Naoaki Okazaki, Takashi Tsunakawa, Jun'ichi Tsujii

Proceedings of the 18th Conference of the Association for Machine Translation in the Americas (AMTA 2008)   2.20 (10 pages)   2008.10

A Discriminative Candidate Generator for String Transformations Reviewed

Naoaki Okazaki, Yoshimasa Tsuruoka, Sophia Ananiadou, Jun'ichi Tsujii

Proceedings of the 2008 Conference on Empirical Methods in Natural Language Processing (EMNLP 2008)   447 - 456   2008.10

Building a Bilingual Lexicon Using Phrase-based Statistical Machine Translation via a Pivot Language Reviewed

Takashi Tsunakawa, Naoaki Okazaki, Jun'ichi Tsujii

Proceedings of the 22nd International Conference on Computational Linguistics (Coling 2008): Companion volume: Posters and Demonstrations   127 - 130   2008.8

A Discriminative Alignment Model for Abbreviation Recognition Reviewed

Naoaki Okazaki, Sophia Ananiadou, Jun'ichi Tsujii

Proceedings of the 22nd International Conference on Computational Linguistics (Coling 2008)   657 - 664   2008.8

Kleio: a knowledge-enriched information retrieval system for biology Reviewed

Chikashi Nobata, Philip Cotter, Naoaki Okazaki, Brian Rea, Yutaka Sasaki, Yoshimasa Tsuruoka, Jun'ichi Tsujii, Sophia Ananiadou

Proceedings of the 31st annual international ACM SIGIR conference on Research and development in information retrieval (SIGIR '08)   787 - 788   2008.7

Connecting Text Mining and Pathways using the PathText Resource Reviewed

Rune Sætre, Brian Kemper, Kanae Oda, Naoaki Okazaki, Yukiko Matsuoka, Norihiro Kikuchi, Hiroaki Kitano, Yoshimasa Tsuruoka, Sophia Ananiadou, Jun’ichi Tsujii

Proceedings of the Sixth International Language Resources and Evaluation (LREC'08)   1736 - 1740   2008.5

Building Bilingual Lexicons using Lexical Translation Probabilities via Pivot Languages Reviewed

Takashi Tsunakawa, Naoaki Okazaki, Jun’ichi Tsujii

Proceedings of the Sixth International Language Resources and Evaluation (LREC'08)   1664 - 1667   2008.5

PathText: Text Mining Tools Integrated with Biological Pathway Reviewed

Rune Sætre, Brian Kemper, Kanae Oda, Naoaki Okazaki, Yukiko Matsuoka, Nobuo Kikuchi, Hiroyuki Kitano, Yoshimasa Tsuruoka, Sophia Ananiadou, Jun'ichi Tsujii

Genomes to Systems Conference 2008   65   2008.3

A Discriminative Approach to Japanese Abbreviation Extraction Reviewed

Naoaki Okazaki, Mitsuru Ishizuka, Jun'ichi Tsujii

Proceedings of the Third International Joint Conference on Natural Language Processing (IJCNLP 2008)   889 - 894   2008.1

Identifying Sections in Scientific Abstracts using Conditional Random Fields Reviewed

Kenji Hirohata, Naoaki Okazaki, Sophia Ananiadou, Mitsuru Ishizuka

Proceedings of the Third International Joint Conference on Natural Language Processing (IJCNLP 2008)   381 - 388   2008.1

SemText: a semantically enriched information retrieval system for biology Reviewed

Sophia Ananiadou, Philip Cotter, Chikashi Nobata, Naoaki Okazaki, Brian Rea, Yutaka Sasaki, Yoshimasa Tsuruoka, Jun'ichi Tsujii

Proceedings of the Eighth International Conference on Systems Biology (ICSB2007)   G35   2007.10

位置履歴からのユーザ属性の推定 Reviewed

松尾豊, 岡崎直観, 中村嘉志, 西村 拓一, 橋田浩一, 中島秀之

情報処理学会論文誌   48 ( 6 )   2106 - 2117   2007.6

Inferring Long-term User Properties based on Users' Location History Reviewed

Yutaka Matsuo, Naoaki Okazaki, Kiyoshi Izumi, Yoshiyuki Nakamura, Takuichi Nishimura, Koiti Hasida, Hideyuki Nakashima

Proceedings of the 20th International Joint Conference on Artificial Intelligence (IJCAI 2007)   2159 - 2165   2007.1

Building an Abbreviation Dictionary Using a Term Recognition Approach Reviewed

Naoaki Okazaki, Sophia Ananiadou

Bioinformatics   22 ( 24 )   3089 - 3095   2006.12

Products Designed on Scenario Maps using Pictorial KeyGraph Reviewed

Kenich Horie, Yukio Ohsawa, Naoaki Okazaki

WSEAS Transactions on Information Science & Applications   3 ( 7 )   1324 - 1331   2006.7

A Term Recognition Approach to Acronym Recognition Reviewed

Naoaki Okazaki, Sophia Ananiadou

Proceedings of the COLING/ACL 2006 Main Conference Poster Sessions   643 - 650   2006.7

A Bottom-Up Approach to Sentence Ordering for Multi-Document Summarization Reviewed

Danushka Bollegala, Naoaki Okazaki, Mitsuru Ishizuka

Proceedings of the 21st International Conference on Computational Linguistics and 44th Annual Meeting of the Association for Computational Linguistics   385 - 392   2006.7

Clustering acronyms in biomedical text for disambiguation Reviewed

Naoaki Okazaki, Sophia Ananiadou

Proceedings of fifth international conference on Language Resources and Evaluation (LREC 2006)   959 - 962   2006.5

Towards a terminological resource for biomedical text mining Reviewed

Goran Nenadic, Naoki Okazaki, Sophia Ananiadou

Proceedings of fifth international conference on Language Resources and Evaluation (LREC 2006)   1071 - 1076   2006.5

An Extension of the Multimodal Presentation Markup Language (MPML) to a Three-dimensional VRML Space Reviewed

Naoaki Okazaki, Santi Saeyor, Hiroshi Dohi, Mitsuru Ishizuka

Systems and Computers in Japan   36 ( 14 )   69 - 80   2005.12

A Machine Learning Approach to Sentence Ordering for Multidocument Summarization and its Evaluation Reviewed

Danushka Bollegala, Naoaki Okazaki, Mitsuru Ishizuka

Proc. of 2nd International Joint Conference on Natural Language Processing (IJCNLP)   624 - 635   2005.10

Improving Chronological Ordering of Sentences Extracted from Multiple Newspaper Articles Reviewed

Naoaki Okazaki, Yutaka Matsuo, Mitsuru Ishizuka

ACM Transactions on Asian Language Information Processing (TALIP) (Special Issue on NTCIR-4: Information Access towards Asian Languages)   4 ( 3 )   321 - 339   2005.9

Understanding Scenarios of Individual Patients of Hepatitis in Double Helical Process Involving KeyGraph and DSV Reviewed

Yukio Ohsawa, Naohiro Matsumura, Naoaki Okazaki

The Fourth IEEE International Workshop on Soft Computing as Transdisciplinary Science and Technology (WSTST05)   456 - 469   2005.5

修辞構造のアノテーションに基づく要約生成 Reviewed

綾 聡平, 松尾 豊, 岡崎 直観, 橋田 浩一, 石塚 満

人工知能学会論文誌   20 ( 3 )   149 - 158   2005.5

Coherent Arrangement of Sentences Extracted from Multiple Newspaper Articles Reviewed

Naoaki Okazaki, Yutaka Matsuo, Mitsuru Ishizuka

PRICAI 2004: Trends in Artificial Intelligence: 8th Pacific Rim International Conference on Artificial Intelligence   882 - 891   2004.8

Improving Chronological Sentence Ordering by Precedence Relation Reviewed

Naoaki Okazaki, Yutaka Matsuo, Mitsuru Ishizuka

Proc. 20th International Conference on Computational Linguistics (COLING 04)   750 - 756   2004.8

TISS: An Integrated Summarization System for TSC-3 Reviewed

Naoaki Okazaki, Yutaka Matsuo, Mitsuru Ishizuka

Working Notes of the Fourth NTCIR Workshop Meeting (NTCIR-4)   2004.6

GDQA: Graph Driven Question Answering System – NTCIR-4 QAC2 Experiments – Reviewed

Gakuto Kurata, Naoaki Okazaki, Mitsuru Ishizuka

Working Notes of the Fourth NTCIR Workshop Meeting (NTCIR-4)   2004.6

Process to Discovering Iron Decrease as Chance to Use Interferon to Hepatitis B Reviewed

Yukio Ohsawa, Hajime Fujie, Akio Saiura, Naoaki Okazaki, Naohiro Matsumura

Proceedings of the Third International Workshop on Active Mining (AM-2004)   21 - 30   2004.6

Scripting and Evaluating Affective Interactions with Embodied Conversational Agents Reviewed

Helmut Prendinger, Junichiro Mori, Santi Saeyor, Kyoshi Mori, Naoaki Okazaki, Yustinus Juli, Sonja Mayer, Hiroshi Dohi, Mitsuru Ishizuka

Künstliche Intelligenz Zeitschrift (German Journal of Artificial Intelligence)   1   4 - 10   2004.2

A Scenario Development on Hepatitis B and C Reviewed

Yukio Ohsawa, Naoaki Okazaki, Naohiro Matsumura, Aiko Saiura, Hajime Fujie

Second International Workshop on Active Mining (AM-2003)   130 - 140   2003.10

Sentence Extraction by Spreading Activation through Sentence Similarity Reviewed

Naoaki Okazaki, Yutaka Matsuo, Naohiro Matsumura, Mitsuru Ishizuka

IEICE Transactions on Information and Systems (Special Issue on Text Processing for Information Access)   E86-D ( 9 )   1686 - 1694   2003.9

Story-Based Planning in Theme Park Reviewed

Yutaka Matsuo, Shigeyoshi Hiratsuka, Tomohisa Yamashita, Akira Takagi, Naoaki Okazaki, Takuji Tokiwa, Koichi Kurumatani

Multi-Agent for Mass User Support: International Workshop (MAMUS 2003)   70 - 85   2003.8

Polaris: An Integrated Data Miner for Chance Discovery Reviewed

Naoaki Okazaki, Yukio Ohsawa

Workshop of Chance Discovery and Its Management (in conjunction with International Human Computer Interaction Conference (HCI2003))   27 - 30   2003.6

Sentence Extraction by Spreading Activation with Refined Similarity Measure Reviewed

Naoaki Okazaki, Yutaka Matsuo, Naohiro Matsumura, Mitsuru Ishizuka

The 16th Florida Artificial Intelligence Research Society Conference (FLAIRS-16)   407 - 411   2003.5

A Multimodal Presentation Markup Language MPML-VR for a 3D Virtual Space Reviewed

Naoaki Okazaki, Sohei Aya, Santi Saeyor, Mitsuru Ishizuka

Workshop Proc. (CD-ROM) on Virtual Conversational Characters: Applications, Methods, and Research Challenges (in conjunction with HF2002 and OZCHI2002)   2002.11

Two Different Methods at NTCIR3-TSC2: Coverage Oriented and Focus Oriented Reviewed

Naoaki Okazaki, Yutaka Matsuo, Naohiro Matsumura, Hironori Tomobe, Mitsuru Ishizuka

NTCIR Workshop 3: Proceedings of the Third NTCIR Workshop on Research in Information Retrieval, Automatic Text Summarization and Question Answering   2002.10

マルチモーダルプレゼンテーション記述言語MPMLの3次元VRML空間への拡張 Reviewed

岡崎 直観, Santi Saeyor, 土肥 浩, 石塚 満

電子情報通信学会論文誌 D-I   J85-D-I ( 9 )   915 - 926   2002.9

Extracting Characteristic Sentences from Related Documents Reviewed

Naoaki Okazaki, Yutaka Matsuo, Naohiro Matsumura, Hironori Tomobe, Mitsuru Ishizuka

6th International Conference on Knowledge-based Intelligent Information Engineering Systems and Applied Technologies (KES2002)   1257 - 1261   2002.9

畳み込みニューラルネットワークを用いた表ラベリングによる固有表現認識と関係抽出

MA Youmi, 平岡達也, 岡崎直観

言語処理学会年次大会発表論文集(Web)   28th   2022

研究会報告：国際シンポジウムJSAI International Symposia on AI 2020（JSAI-isAI 2020）開催報告

岡崎 直観, 矢田 勝俊

人工知能   374 - 376   2021.5

企業情報を考慮したキャッチコピーの自動生成

昇夏海, 平岡達也, 丹羽彩奈, 西口佳佑, 岡崎直観

言語処理学会年次大会発表論文集(Web)   27th   2021

BERTを用いたTable-Fillingによる固有表現抽出と関係抽出

MA Youmi, 平岡達也, 岡崎直観

言語処理学会年次大会発表論文集(Web)   27th   2021

後段モデルの損失値を用いた単語分割のタスクへの最適化

平岡達也, 高瀬翔, 内海慶, 欅惇志, 岡崎直観

言語処理学会年次大会発表論文集(Web)   27th   2021

言語処理100本ノック Invited

岡崎 直観, 清野 舜, 高橋 諒, 横井 祥

自然言語処理   703 - 710   2020.9

国際シンポジウムJSAI International Symposia on AI 2019（JSAI-isAI 2019）開催報告

坂本 真樹, 岡崎 直観

人工知能   282 - 285   2020.3

RNNにより高次の依存を考慮したニューラル隠れマルコフモデル

平岡達也, 高瀬翔, 内海慶, 欅惇志, 岡崎直観

言語処理学会年次大会発表論文集(Web)   26th   2020

RNNによる遷移確率計算を用いた隠れマルコフモデル

平岡達也, 高瀬翔, 内海慶, 欅惇志, 岡崎直観

情報処理学会研究報告(Web)   2019 ( NL-242 )   2019

ロボットジャーナリズムの現状と課題 Invited

岡崎 直観

映像情報メディア学会誌   70 - 75   2018.3

自然言語文からの関係知識ベースの構築 Invited

高瀬 翔, 岡崎 直観

知能と情報（日本知能情報ファジィ学会誌）   55 - 64   2017.4

NLP 若手の会 Invited

海野 裕也, 岡崎 直観, 西川 仁, 中澤 敏明

人工知能   266 - 267   2017.3

条件付き確率場の理論と実践 Invited

岡崎 直観

統計数理   2016.12

データジャーナリズムとデータ科学 Invited

岡崎 直観

電子情報通信学会誌   339 - 346   2016.4

言語処理における分散表現学習のフロンティア Invited

岡崎 直観

人工知能   189 - 201   2016.3

3.12 Web応用タスクにおけるエラー分析 -Twitterを用いた疾患サーベイランスを題材に- Invited

荒牧 英治, 岡崎 直観

情報処理   32 - 33   2015.12

言語処理が社会に浸透するには Invited

岡崎 直観

人工知能   20   2015.1

「人工知能」の表紙に関するTweetの分析

鳥海 不二夫, 榊 剛史, 岡崎 直観

人工知能   172 - 181   2014.3

言語処理による分析 — 日本栄養士会活動報告の分析

岡崎 直観, 鍋島 啓太, 乾 健太郎

日本栄養士会雑誌   6 - 8   2012.12

学生フォーラム（黒橋 禎夫 氏インタビュー）

内海 ゆづ子, 岡崎 直観

人工知能学会誌   577 - 579   2007.7

学生フォーラム（喜連川 優 氏インタビュー）

岡崎 直観, 西原 陽子

人工知能学会誌   633 - 634   2006.9

学生フォーラム（溝口 理一郎 氏インタビュー）

金崎弘文, 岡崎 直観

人工知能学会誌   245 - 247   2005.3

学生フォーラム（辻井 潤一 氏インタビュー）

濱崎雅弘, 岡崎 直観

人工知能学会誌   733 - 736   2004.11

従属性に基づく事態間関係知識の粒度調整

横井 祥, 持橋 大地, 岡崎 直観, 乾 健太郎

言語処理学会第23回年次大会 (NLP2017)  2017.3 

自然言語処理を支える大規模計算資源 Invited

岡崎 直観

第２回データサイエンス支援サービスシンポジウム  2017.6 

Modelling Relationships between Objects for Referring Expression Comprehension

冉 文升, 田 然, 岡崎 直観, 乾 健太郎

第232回自然言語処理研究会  2017.7 

独立性尺度に基づく知識の粒度の教師なし推定

横井 祥, 持橋 大地, 高橋 諒, 岡崎 直観, 乾 健太郎

第31回人工知能学会全国大会  2017.5 

複単語表現を利用した因果関係推定モデルの改善

佐々木 翔大, 高瀬 翔, 井之上 直也, 岡崎 直観, 乾 健太郎

第231回自然言語処理研究会・第116回音声言語情報処理研究会  2017.5 

独立性判定基準に基づく知識の汎化

横井 祥, 持橋 大地, 岡崎 直観, 乾 健太郎

第11回NLP若手の会シンポジウム  2016.8 

共参照関係に基づく分散表現の共有と動的更新

小林 颯介, 岡崎 直観, 乾 健太郎

第11回NLP若手の会シンポジウム  2016.8 

分散表現を用いた因果関係のモデル化

佐々木 翔大, 高瀬 翔, 井之上 直也, 岡崎 直観, 乾 健太郎

第11回NLP若手の会シンポジウム  2016.8 

seq2seqモデルに基づく略語の自動生成

鶴田 崇仁, 松田 耕史, 岡崎 直観, 乾 健太郎

第11回NLP若手の会シンポジウム  2016.8 

質問応答データセットと文章読解モデルの比較・検討

清野 舜, 岡崎 直観, 乾 健太郎

第11回NLP若手の会シンポジウム  2016.8 

Learning to Describe Product Images from Noisy Online Data

Takuya Yashima, Naoaki Okazaki, Kentaro Inui, Kota Yamaguchi, Takayuki Okatani

第19回画像の認識・理解シンポジウム (MIRU2016)  2016.8 

自然言語処理における深層ニューラルネットワーク Invited

岡崎 直観

Prometech Simulation Conference 2016 Deep Learning セッション 講演2  2016.9 

Knowledge acquisition using deep neural network

Naoaki Okazaki

The International Symposium on Designing Semantics  2017.3 

談話関係認識のための時制情報の分析

清野 舜, 田 然, 渡邉 研斗, 岡崎 直観, 乾 健太郎

言語処理学会第23回年次大会 (NLP2017)  2017.3 

言語処理における常識的知識の獲得・活用 Invited

岡崎 直観

第32回ファジィシステムシンポジウム  2016.9 

自然言語処理におけるDeep Learning Invited

岡崎 直観

電子情報通信学会総合大会 2017 企画セッション 「もっと知りたい！ Deep Learning ～基礎から活用まで～」  2017.3 

日本語Wikificationコーパスの構築に向けて

Davaajav Jargalsaikhan, 岡崎 直観, 松田 耕史, 乾 健太郎

言語処理学会第22回年次大会  2016.3 

Wikipedia記事に対する拡張固有表現ラベルの多重付与

鈴木 正敏, 松田 耕史, 関根 聡, 岡崎 直観, 乾 健太郎

言語処理学会第22回年次大会  2016.3 

利用物に関する知識のコーパスアノテーション

上村 明衣, 折田 奈甫, 岡崎 直観, 乾 健太郎

言語処理学会第22回年次大会  2016.3 

画像説明文生成に向けた物体間の関係の認識

村岡 雅康, Sumit Maharjan, 齋藤 真樹, 山口 光太, 岡崎 直観, 岡谷 貴之, 乾 健太郎

言語処理学会第22回年次大会  2016.3 

分散表現による文脈情報を用いた選択選好モデル

大野 雅之, 井之上 直也, 松林 優一郎, 岡崎 直観, 乾 健太郎

言語処理学会第22回年次大会  2016.3 

感情状態に基づく因果関係推論の一般化

井之上 直也, 岡崎 直観, 乾 健太郎

言語処理学会第22回年次大会  2016.3 

談話内における局所文脈の動的分散表現

小林 颯介, 田 然, 岡崎 直観, 乾 健太郎

言語処理学会第22回年次大会  2016.3 

言葉を理解する人工知能のいま ～自然言語処理の基礎からフロンティアまで～ Invited

乾 健太郎, 岡崎 直観

平成28年度東北大学・カタールサイエンスキャンパス第２回教育セミナー  2016.8 

Wikipediaを知識源に用いた早押しクイズの解法の検討

鈴木 正敏, 松田 耕史, 関根 聡, 岡崎 直観, 乾 健太郎

第11回NLP若手の会シンポジウム  2016.8 

深層ニューラルネットワークによる知識の自動獲得や推論 Invited

岡崎 直観

第71回人工知能セミナー「Deep Learning技術の仕組みと自然言語処理への応用」  2016.6 

自然言語処理における深層ニューラルネットワーク研究のフロンティア Invited

岡崎 直観

電子情報通信学会 バイオメトリクス研究専門委員会（BioX） 2016年度8月研究会  2016.8 

対数的共起ベクトルの加法構成性

田 然, 岡崎 直観, 乾 健太郎

情報処理学会研究報告 自然言語処理（NL） 2015-NL-221(14)  2015.5 

単語分散表現のshift-reduce型構文解析への利用

小松 広弥, 田 然, 岡崎 直観, 乾 健太郎

情報処理学会研究報告 自然言語処理（NL） 2015-NL-221(3)  2015.5 

関係知識獲得のための意味表現の学習

高瀬 翔, 岡崎 直観, 乾 健太郎

2015年度人工知能学会全国大会（第29回）  2015.5 

Twitterを利用した地域毎の要望抽出

栗原 理聡, 佐々木 彬, 松田 耕史, 岡崎 直観, 乾 健太郎

2015年度人工知能学会全国大会（第29回）  2015.5 

Exploring the Challenges of Entity Linking in Knowledge-based Question Answering

周 双双, 岡崎 直観, 乾 健太郎

第10回NLP若手の会シンポジウム  2015.9 

Determining Argument Strength and Consistency using a Causality-based Knowledge Graph

Paul Reisert, Naoya Inoue, Naoaki Okazaki, Kentaro Inui

第10回NLP若手の会シンポジウム  2015.9 

Wikipediaエントリの拡張固有表現階層への自動分類

鈴木 正敏, 松田 耕史, 関根 聡, 岡崎 直観, 乾 健太郎

第10回NLP若手の会シンポジウム  2015.9 

分散表現に基づく選択選好モデルの文脈化

大野 雅之, 井之上 直也, 松林 優一郎, 岡崎 直観, 乾 健太郎

情報処理学会研究報告 自然言語処理（NL） 2016-NL-225(1)  2016.1 

研究室における研究・実装ノウハウの共有

岡崎 直観

言語処理学会第22回年次大会ワークショップ「論文に書かない(書けない)自然言語処理」  2016.3 

言葉を操るコンピューターの最前線 Invited

岡崎直観

ITFOR ユーザー会 エグゼクティブセミナー  2015.10 

単語・句の分散表現の学習 Invited

岡崎直観

WebDB Forum 2015 特別セッション3: Deep Learningと自然言語処理  2015.11 

大規模言語データに基づく自然言語処理とその応用 Invited

岡崎直観

第17回情報論的学習理論ワークショップ(IBIS2014) 企画セッション4: 機械学習のウェブデータおよびマルチメディア活用  2014.11 

アルゴリズムが果たすジャーナリズムへの貢献 Invited

岡崎直観, 徳永拓之, 中路紘平, 西岡悠平

SmartNews Compass 2014  2014.12 

近似頻度計測手法を用いた大規模データからの関係獲得

高瀬 翔, 岡崎 直観, 乾 健太郎

情報処理学会研究報告 自然言語処理（NL） 2014-NL-217(9)  2014.7 

言語処理がつなぐビッグデータと社会 Invited

岡崎直観

言語処理学会20周年記念シンポジウム  2014.10 

キーワードの自動拡張に基づくイベント言及ツイートの収集

五十嵐 祐貴, 大野 雅之, 岡崎 直観, 乾 健太郎

言語処理学会第21回年次大会  2015.3 

構成性に基づく関係パタンの意味計算

高瀬 翔, 岡崎 直観, 乾 健太郎

言語処理学会第21回年次大会  2015.3 

場所参照表現タグ付きコーパスの構築と評価

松田 耕史, 佐々木 彬, 岡崎 直観, 乾 健太郎

情報処理学会研究報告 自然言語処理（NL）  2015.1 

言語処理による災害情報の分析と集約 Invited

岡崎直観

情報処理学会 第196回コンピュータビジョンとイメージメディア研究発表会  2015.3 

単語の分散表現と構成性の計算モデルの発展 Invited

岡崎直観

2015年度人工知能学会全国大会(第29回), OS-1 意味と理解のコンピューティング (2)  2015.5 

Bi-gram連接表と単語列変形規則に基づく回文自動生成

清野 舜, 渡邉 研斗, 岡崎 直観, 乾 健太郎

2015年度人工知能学会全国大会（第29回）  2015.5 

Learning Visual Attributes from Image and Text

Maharjan Sumit, 齋藤 真樹, 山口 光太, 岡崎 直観, 岡谷 貴之, 乾 健太郎

言語処理学会第21回年次大会  2015.3 

インターネット上の当選運動・落選運動の分析

船木 洋晃, 佐々木 彬, 岡崎 直観, 乾 健太郎, 深田 陽介, 竹下 隆一郎, 田森 秀明, 野澤 博

人工知能学会第28回全国大会  2014.5 

高速な類似度計算手法による関係パタンのクラスタリング

高瀬 翔, 岡崎 直観, 乾 健太郎

言語処理学会第20回年次大会  2014.3 

An Investigation of Evidence Relations within Social Media Conversations

Paul Reisert, Junta Mizuno, Miwa Kanno, Naoaki Okazaki, Kentaro Inui

言語処理学会第20回年次大会  2014.3 

ジャーナリズム再考：ビッグデータとテクノロジー Invited

岡崎直観, 津田大介, 奥山晶二郎

ソーシャルメディアウィーク東京2014  2014.2 

大規模言語モデルはどこまで賢くなるのか？ Invited

岡崎 直観

第15回 東京科学大学ITクラブ ・ 蔵前ITコミュニティ合同セミナー 「AIの現状と未来」  2025.7 

自然言語処理によるビッグデータ分析 Invited

岡崎直観

宮城野ロータリークラブ通常例会  2014.3 

係り受け関係を用いた句ベクトルの生成

村岡 雅康, 島岡 聖世, 山本 風人, 渡邉 陽太郎, 岡崎 直観, 乾 健太郎

言語処理学会第20回年次大会  2014.3 

「人工知能」の表紙に関するツイートの分析・続報

鳥海 不二夫, 榊 剛史, 岡崎 直観

第4回Webインテリジェンスとインタラクション研究会（WI2研究会）, (9)  2014.5 

実世界指向情報構造化支援のための情報抽出技術

渡邉 陽太郎, 佐々木 彬, 五十嵐 祐貴, 岡崎 直観, 乾 健太郎

言語処理学会第20回年次大会  2014.3 

ガウス分布による単語と句の意味の分布的表現

島岡 聖世, 村岡 雅康, 山本 風人, 渡邉 陽太郎, 岡崎 直観, 乾 健太郎

言語処理学会第20回年次大会  2014.3 

言葉を操るコンピュータの最前線 — 自然言語処理の基礎からビッグデータへの応用まで Invited

岡崎直観

QuickSolutionイノベーション・フォーラム2014  2014.6 

Word2vecの並列実行時の学習速度の改善

岡崎 直観, 乾 健太郎

情報処理学会研究報告 自然言語処理（NL） 2014-NL-217(8)  2014.7 

大規模言語モデルはデータ漏洩を隠蔽できるのか

高橋 侑成, Youmi Ma, 金子 正弘, 岡崎 直観

言語処理学会第31回年次大会 (NLP2025)  2025.3 

Mitigating Social Bias in Large Language Models by Self-Correction

Panatchakorn Anantaprayoon, 金子 正弘, 岡崎 直観

言語処理学会第31回年次大会 (NLP2025)  2025.3 

LLM-jp-3 VILA: 日本語マルチモーダルデータセット及び強力な日本語マルチモーダルモデルの構築

笹川 慶人, 前田 航希, 杉浦 一瑳, 栗田 修平, 岡崎 直観, 河原 大輔

言語処理学会第31回年次大会 (NLP2025)  2025.3 

複数タスク・複数項目に跨ったマルチモーダル自動評価手法

大井 聖也, 金子 正弘, 岡崎 直観, 井上 中順

言語処理学会第31回年次大会 (NLP2025)  2025.3 

安全な大規模言語モデルの構築と利用を目指して Invited

岡崎 直観, 金子 正弘

2025年度人工知能学会全国大会（第39回）オーガナイズドセッション OS-42「大規模言語モデルの安全対策 ― 大いなる力には、大いなる責任が伴う」  2025.5 

大規模言語モデルの発展 Invited

岡崎 直観

2025年度人工知能学会全国大会（第39回）企画セッション KS-2「人工知能学会・日本神経回路学会合同企画「AI for Science」」  2025.5 

Swallowコーパスv2: 教育的な日本語ウェブコーパスの構築

服部 翔, 岡崎 直観, 水木 栄, 藤井 一喜, 中村 泰士, 大井 聖也, 塩谷 泰平, 齋藤 幸史郎, Youmi Ma, 前田 航希, 岡本 拓己, 石田 茂樹, 横田 理央, 高村 大也

言語処理学会第31回年次大会 (NLP2025)  2025.3 

日本の文化常識・日常生活知識理解のための視覚言語ベンチマーク MECHA-Ja の構築

前田航希, 長谷川騎平, 栗田修平, 小田悠介, 徳久良子, 岡崎直観

情報処理学会 第263回自然言語処理研究会 研究報告 (2024-NL-263)  2025.3 

自ら進化する大規模言語モデル: LLMによるLLMのためのLLM開発 Invited

岡崎 直観

画像の認識・理解シンポジウムMIRU2025 特別講演  2025.7 

情報信頼性の検証への自然言語処理的アプローチ

乾 健太郎, 岡崎 直観

人工知能学会第69回言語・音声理解と対話処理研究会(SIG-SLUD)  2013.12 

大規模言語モデルの開発 Invited

岡崎 直観

情報処理学会連続セミナー2025「AIが拓く次世代イノベーション」  2025.7 

東京科学大学と産業技術総合研究所「Swallow」プロジェクト Gemma 2が拓く日本語LLMの未来 Invited

岡崎 直観

The Beyond Series: Research@Tokyo - Co-imagine the Future of Society with AI -  2025.6 

llm-jp-eval-mm: 日本語視覚言語モデルの自動評価基盤

前田 航希, 杉浦 一瑳, 小田 悠介, 栗田 修平, 岡崎 直観

言語処理学会第31回年次大会 (NLP2025)  2025.3 

Jailbreakにより生成したフェイクニュースの危険度評価

島田 比奈理, 金子 正弘, 岡崎 直観

言語処理学会第31回年次大会 (NLP2025)  2025.3 

大規模言語モデルの多言語社会的バイアス抑制における単言語ラベル付きデータの役割

大葉 大輔, 金子 正弘, Danushka Bollegala, 岡崎 直観

言語処理学会第31回年次大会 (NLP2025)  2025.3 

新聞記事からつくる 時事と社会に強い日本語LLM

服部 翔, 水木 栄, 藤井 一喜, 中村 泰士, 塩谷 泰平, 植田 快, 新妻 巧朗, 川畑 輝, 田森 秀明, Youmi Ma, 前田 航希, 大井 聖也, 齋藤 幸史郎, 岡本 拓己, 石田 茂樹, 横田 理央, 高村 大也, 岡崎 直観

言語処理学会第31回年次大会 (NLP2025)  2025.3 

模倣学習による大規模言語モデルの指示チューニング

Youmi Ma, 水木 栄, 藤井 一喜, 中村 泰士, 大井 聖也, 島田 比奈理, 塩谷 泰平, 齋藤 幸史郎, 前田 航希, 服部 翔, 岡本 拓己, 石田 茂樹, 横田 理央, 高村 大也, 岡崎 直観

言語処理学会第31回年次大会 (NLP2025)  2025.3 

時事情報に関する日本語QAベンチマーク『ニュースQ』

植木 快, 川畑 輝, 田口 雄哉, 新妻 巧朗, 浦川 通, 田森 秀明, 岡崎 直観, 乾 健太郎

言語処理学会第31回年次大会 (NLP2025)  2025.3 

オープンLLMによる翻訳を活用した日本語CLIPの開発

杉浦 一瑳, 栗田 修平, 小田 悠介, 河原 大輔, 岡崎 直観

言語処理学会第31回年次大会 (NLP2025)  2025.3 

PUPPET：タスク性能を維持しながらLLMとして検出されやすくする学習フレームワーク

齋藤 幸史郎, 小池 隆斗, 金子 正弘, 岡崎 直観

言語処理学会第31回年次大会 (NLP2025)  2025.3 

SOMO: 音声認識出力の可読性向上を目的とした整文手法の提案

杉野 かおり, 山野 陽祐, 河崎 真琴, 田森 秀明, 岡崎 直観, 乾 健太郎

言語処理学会第31回年次大会 (NLP2025)  2025.3 

バナー広告における画像と広告コピーの評価ベンチマーク構築

遠藤 洸亮, 脇本 宏平, 宮西 洋輔, 岡崎 直観

言語処理学会第31回年次大会 (NLP2025)  2025.3 

視覚言語モデルの識別性能に関する評価用ベンチマークの構築

村岡 雅康, 岡崎 直観

言語処理学会第31回年次大会 (NLP2025)  2025.3 

Adapting Overseas Large Language Models to Japanese Invited International conference

Naoaki Okazaki

4th International Forum on Energy & Informatics  2024.12 

大規模言語モデルはどのように「ことばの壁」を超えるのか Invited

岡崎 直観

第8回自動翻訳シンポジウム  2025.2 

Japanese and Korean developers share their experiences with Gemma (Fireside Chat) Invited

Jetha Chan, Ju-yeong Ji, Naoaki Okazaki, Junbum Lee

Gemma Developer Day in Tokyo  2024.10 

The Global View on (local) LLMs in US, Europe and Asia (Panel Discussion) Invited

Preslav Nakov, Noah Smith, Naoaki Okazaki, Sebastian Arnold

Shonan Meeting 209: Empowering Local Open Source LLMs  2024.10 

基盤モデルの最先端と科学研究での活用 Invited

岡崎 直観

CBI学会2024年大会 招待講演「LLMの最先端トピックス」  2024.10 

日本における生成AI普及への挑戦 〜国産LLMはどう貢献できるか (パネル討論) Invited

丹波 廣寅, 林 達, 岡崎 直観, 横田 理央, 渡辺 琢也

Generative AI Summit (GenAI/Sum): 生成AIが起こす “シン”産業革命  2024.10 

日本語に強い大規模言語モデルSwallowの構築 Invited

岡崎 直観

第49回蔵前科学技術セミナー「AIの光と影」  2024.11 

マルチモーダル基盤モデルと教育への応用 Invited

岡崎 直観

第82回 大学等におけるオンライン教育とデジタル変革に関するサイバ ーシンポジウム  2024.11 

大規模言語モデルの最前線と医療・ヘルスケアへの応用 Invited

岡崎 直観

CHUGAI INNOVATION DAY 2024, Session 1「生成AIが変えるヘルスケアの未来想像図」  2024.11 

日本語に強い大規模言語モデルのレシピ Invited

岡崎 直観

NVIDIA AI Summit Japan  2024.11 

日本語に特化した大規模言語モデルの現状と展望 Invited

岡崎 直観

計測自動制御学会定時社員総会  2025.3 

LLMに日本語テキストを学習させる意義

齋藤 幸史郎, 水木 栄, 大井 聖也, 中村 泰士, 塩谷 泰平, 前田 航希, 馬 尤咪, 服部 翔, 藤井 一喜, 岡本 拓己, 石田 茂樹, 高村 大也, 横田 理央, 岡崎 直観

情報処理学会 第261回自然言語処理研究会 研究報告 (2024-NL-261)  2024.9 

大規模言語モデルによる日本文化に沿った指示データ生成

塩谷 泰平, 金子 正弘, 岡崎 直観

第19回YANSシンポジウム (YANS2024)  2024.9 

強化学習を用いた、言語理解能力を維持したLLM検出器の性能向上

齋藤 幸史郎, 小池 隆斗, 金子 正弘, 岡崎 直観

第19回YANSシンポジウム (YANS2024)  2024.9 

マルチモーダルWG Invited

岡崎 直観

LLMシンポジウム2024「大規模言語モデルのあるべき姿とは？」  2024.9 

大規模言語モデルSwallowの現状と展望 Invited

岡崎 直観

学術変革B「身体記号学」領域会議 招待講演  2024.9 

大規模言語モデルの仕組みと生命医学分野での展望 Invited

岡崎 直観

第34回日本心臓核医学会総会・学術大会 シンポジウム2「人工知能による診断支援の可能性：機械学習・深層学習・大規模言語モデル」  2024.6