Thesis

Journal papers

  • Yusuke Sakai, Hidetaka Kamigaito, Katsuhiko Hayashi and Taro Watanabe. 2024. Investigation of the Inference Capabilities and Memorization of Pre-trained Language Models. Journal of Natural Language Processing (to appear).

  • Yuya Sawada, Yuichiro Yasui, Hiroki Ouchi, Taro Watanabe, Masayuki Ishii, Shotaro Ishihara, Takeshi Yamada and Hiroyuki Shindo. 2024. Constraction and Analysis of Similarity-based EL System for Nikkei Company ID Linking. Journal of Natural Language Processing.

  • Kosuke Doi, Katsuhito Sudoh and Satoshi Nakamura. 2024. NAIST Simultaneous Interpretation Corpus: Development and Analyses of Data from Interpreters of Different Levels. Journal of Natural Language Processing.

  • Huy Hien Vu, Hidetaka Kamigaito and Taro Watanabe. 2024. Context-Aware Machine Translation with Source Coreference Explanation. Transactions of the Association for Computational Linguistics.

  • Miyu Oba, Tatsuki Kuribayashi, Hiroki Ouchi and Taro Watanabe. 2024. Second Language Acquisition of Neural Language Models. Journal of Natural Language Processing.

  • Hiroyuki Deguchi, Taro Watanabe, Yusuke Matsui, Masao Utiyama, Hideki Tanaka and Eiichiro Sumita. 2024. Subset Retrieval Nearest Neighbor Machine Translation. Journal of Natural Language Processing.

  • Jungmin Choi, Ukyo Honda, Taro Watanabe and Kentaro Inui. 2023. Explainable Natural Language Inference in the Legal Domain via Text Generation. Transactions of the Japanese Society for Artificial Intelligence.

  • Van-Hien Tran, Hiroki Ouchi, Hiroyuki Shindo, Yuji Matsumoto and Taro Watanabe. 2023. Enhancing Semantic Correlation between Instances and Relations for Zero-Shot Relation Extraction. Journal of Natural Language Processing.

  • Shintaro Harada and Taro Watanabe. 2022. Neural Machine Translation with Synchronous Latent Phrase Structure. Journal of Natural Language Processing.

  • Yuki Yamamoto, Yuji Matsumoto and Taro Watanabe. 2022. Dependency Patterns of Complex Sentences and Semantic Disambiguation for Abstract Meaning Representation Parsing. Journal of Natural Language Processing.

  • Ukyo Honda, Hashimoto Atsushi, Taro Watanabe and Yuji Matsumoto. 2022. Removing Partial Mismatches in Unsupervised Image Captioning. Transactions of the Japanese Society for Artificial Intelligence.

  • Yiran Wang, Hiroyuki Shindo, Yuji Matsumoto, and Taro Watanabe. 2022. Nested Named Entity Recognition via Explicitly Excluding the Influence of the Best Path. Journal of Natural Language Processing.

  • Hiroki Ouchi, Jun Suzuki, Sosuke Kobayashi, Sho Yokoi, Tatsuki Kuribayashi, Masashi Yoshikawa and Kentaro Inui. 2021. Instance-Based Neural Dependency Parsing. Transactions of the Association for Computational Linguistics.

  • Farjana Sultana Mim, Naoya Inoue, Paul Reisert, Hiroki Ouchi and Kentaro Inui. 2021. Corruption Is Not All Bad: Incorporating Discourse Structure Into Pre-Training via Corruption for Essay Scoring. IEEE/ACM Transactions on Audio, Speech, and Language Processing.

  • Yuya Sawada, Hiroki Teranishi, Yuji Matsumoto and Taro Watanabe. 2021. Coordinate Structure Analysis without Labeled Data for Recognizing Compound Named Entities. Journal of Natural Language Processing.

  • Van-Hien Tran, Van-Thuy Phi, Akihiko Kato, Hiroyuki Shindo, Taro Watanabe and Yuji Matsumoto. 2021. Improved Decomposition Strategy for Joint Entity and Relation Extraction. Journal of Natural Language Processing.

  • Masao Ideuchi, Yohei Sakamoto, Yoshitaka Oida, Isaac Okada, Shohei Higashiyama, Masao Utiyama, Eiichiro Sumita and Taro Watanabe. 2021. A Selection Support System for Enterprise Resource Planning Package Components using Ensembles of Multiple Models with Round-trip Translation. Journal of Natural Language Processing.

  • Hiroyuki Deguchi, Masao Utiyama, Akihiro Tamura, Takashi Ninomiya and Eiichiro Sumita. 2021. Bilingual Subword Segmentation for Neural Machine Translation. Journal of Natural Language Processing.

  • Hiroki Teranishi, Hiroyuki Shindo, Taro Watanabe and Yuji Matsumoto. 2020. Coordinate Structure Analysis using Local Models and CKY Algorithm. Journal of Natural Language Processing.

  • Shohei Higashiyama, Masao Utiyama, Yuji Matsumoto, Taro Watanabe and Eiichiro Sumita. 2020. Auxiliary Lexicon Word Prediction for Cross-Domain Word Segmentation. Journal of Natural Language Processing.

  • Shohei Higashiyama, Masao Utiyama, Eiichiro Sumita, Masao Ideuchi, Yoshiaki Oida, Yohei Sakamoto, Isaac Okada and Yuji Matsumoto. 2020. Character-to-Word Attention for Word Segmentation. Journal of Natural Language Processing. Paper Award

International conferences

  • Hiroyuki Deguchi, Yusuke Sakai, Hidetaka Kamigaito and Taro Watanabe. 2024. mbrs: A Library for Minimum Bayes Risk Decoding. EMNLP 2024 System Demonstration (to appear).

  • Wataru Hashimoto, Hidetaka Kamigaito and Taro Watanabe. 2024. Are Data Augmentation Methods in Named Entity Recognition Applicable for Uncertainty Estimation?. EMNLP 2024 (to appear).

  • Miyu Oba, Yohei Oseki, Akiyo Fukatsu, Akari Haga, Hiroki Ouchi, Taro Watanabe and Saku Sugawara. 2024. Learnability of Indirect Evidence in Language Models. EMNLP 2024 (to appear).

  • Zhe Cao, Zhi Qu, Hidetaka Kamigaito and Taro Watanabe. 2024. Exploring Intrinsic Language-specific Subspaces in Fine-tuning Multilingual Neural Machine Translation. EMNLP 2024 (to appear).

  • Zhiyu Guo, Hidetaka Kamigaito and Taro Watanabe. 2024. Attention Score is not All You Need for Token Importance Indicator in KV Cache Reduction: Value Also Matters. EMNLP 2024 (to appear).

  • Mana Makinae, Yusuke Sakai, Hidetaka Kamigaito and Taro Watanabe. 2024. Simul-MuST-C: Simultaneous Multilingual Speech Translation Corpus Using Large Language Model. EMNLP 2024 (to appear).

  • Yusuke Sakai, Mana Makinae, Hidetaka Kamigaito and Taro Watanabe. 2024. Simultaneous Interpretation Corpus Construction by Large Language Models in Distant Language Pair. EMNLP 2024 (to appear).

  • Huayang Li, Deng Cai, Zhi Qu, Qu Cui, Hidetaka Kamigaito, Lemao Liu and Taro Watanabe. 2024. Cross-lingual Contextualized Phrase Retrieval. EMNLP 2024 Findings (to appear).

  • Tsutomu Hirao, Naoki Kobayashi, Hidetaka Kamigaito, Manabu Okumura ande Akisato Kimura. 2024. Video Discourse Parsing and Its Application to Multimodal Summarization: A Dataset and Baseline Approaches. EMNLP 2024 Findings (to appear).

  • Kazuki Hayashi, Yusuke Sakai, Hidetaka Kamigaito, Katsuhiko Hayashi and Taro Watanabe. 2024. Artwork Explanation in Large-scale Vision Language Models. ACL 2024.

  • Armin Sarhangzadeh and Taro Watanabe. 2024. Alignment-Based Decoding Policy for Low-Latency and Anticipation-Free Neural Japanese Input Method Editors. ACL 2024 Findings.

  • Juseon-Do Juseon-Do, Jingun Kwon, Hidetaka Kamigaito and Manabu Okumura. 2024. InstructCMP: Length Control in Sentence Compression through Instruction-based Large Language Models. ACL 2024 Findings.

  • Huayang Li, Siheng Li, Deng Cai, Longyue Wang, Lemao Liu, Taro Watanabe, Yujiu Yang and Shuming Shi. 2024. TextBind: Multi-turn Interleaved Multimodal Instruction-following in the Wild. ACL 2024 Findings.

  • Hiroyuki Deguchi, Yusuke Sakai, Hidetaka Kamigaito, Taro Watanabe, Hideki Tanaka and Masao Utiyama. 2024. Centroid-Based Efficient Minimum Bayes Risk Decoding. ACL 2024 Findings.

  • Yusuke Sakai, Hidetaka Kamigaito and Taro Watanabe. 2024. mCSQA: Multilingual Commonsense Reasoning Dataset with Unified Creation Strategy by Language Models and Humans. ACL 2024 Findings.

  • Akari Haga, Saku Sugawara, Akiyo Fukatsu, Miyu Oba, Hiroki Ouchi, Taro Watanabe and Yohei Oseki. 2024. Modeling Overregularization in Children with Small Language Models. ACL 2024 Findings.

  • Hiroyuki Deguchi, Masaaki Nagata and Taro Watanabe. 2024. Detector-Corrector: Edit-Based Automatic Post Editing for Human Post Editing. EAMT 2024 (to appear).

  • Yusuke Sakai, Hidetaka Kamigaito, Katsuhiko Hayashi and Taro Watanabe. 2024. Does Pre-trained Language Model Actually Infer Unseen Links in Knowledge Graph Completion?. NAACL 2024.

  • Benjamin Hsu, Xiaoyu Liu, Huayang Li, Yoshinari Fujinuma, Maria Nadejde, Xing Niu, Ron Litman, Yair Kittenplon and Raghavendra Pappagari. 2024. M3T: A New Benchmark Dataset for Multi-Modal Document-Level Machine Translation. NAACL 2024.

  • Eunike Kardinata, Hiroki Ouchi and Taro Watanabe. 2024. Constructing Indonesian-English Travelogue Dataset. LREC-COLING 2024.

  • Frederikus Hudi, Zhi Qu, Hidetaka Kamigaito and Taro Watanabe. 2024. Disentangling Pretrained Representation to Leverage Low-Resource Languages in Multilingual Machine Translation. LREC-COLING 2024.

  • Iqra Ali, Hidetaka Kamigaito and Taro Watanabe. 2024. Monolingual Paraphrase Detection Corpus for Low Resource Pashto Language at Sentence Level. LREC-COLING 2024.

  • Eri Onami, Shuhei Kurita, Taiki Miyanishi and Taro Watanabe. 2024. JDocQA: Japanese Document Question Answering Dataset for Generative Language Models. LREC-COLING 2024.

  • Xincan Feng and Akifumi Yoshimoto. 2024. Llama-VITS: Enhancing TTS Synthesis with Semantic Awareness. LREC-COLING 2024.

  • Shohei Higashiyama, Hiroki Ouchi, Hiroki Teranishi, Hiroyuki Otomo, Yusuke Ide, Aitaro Yamamoto, Hiroyuki Shindo, Yuki Matsuda, Shoko Wakamiya, Naoya Inoue, Ikuya Yamada and Taro Watanabe. 2024. Arukikata Travelogue Dataset with Geographic Entity Mention, Coreference, and Link Annotation. EACL 2024 Findings.

  • Hiroyuki Deguchi, Kenji Imamura, Yuto Nishida, Yusuke Sakai, Justin Vasselli and Taro Watanabe. 2023. NAIST-NICT WMT’23 General MT Task Submission. WMT 2023.

  • Lemao Liu, Francisco Casacuberta, George Foster, Guoping Huang, Philipp Koehn, Geza Kovacs, Shuming Shi, Taro Watanabe and Chengqing Zong. 2023. Findings of the Word-Level AutoCompletion Shared Task in WMT 2023. WMT 2023.

  • Huayang Li, Tian Lan, Zihao Fu, Deng Cai, Lemao Liu, Nigel Collier, Taro Watanabe and Yixuan Su. 2023. Repetition In Repetition Out: Towards Understanding Neural Text Degeneration from the Data Perspective. NeurIPS 2023.

  • Yiran Wang, Taro Watanabe, Masao Utiyama and Yuji Matsumoto. 2023. 24-bit Languages. IJCNLP-AACL 2023.

  • Xincan Feng, Hidetaka Kamigaito, Katsuhiko Hayashi and Taro Watanabe. 2023. Model-based Subsampling for Knowledge Graph Completion. IJCNLP-AACL 2023.

  • Shuhei Kurita, Naoki Katsura and Eri Onami. 2023. RefEgo: Referring Expression Comprehension Dataset from First-Person Perception of Ego4D. ICCV 2023.

  • Chihiro Taguchi, Yusuke Sakai, Parisa Haghani and David Chiang. 2023. Universal Automatic Phonetic Transcription into the International Phonetic Alphabet. Interspeech 2023.

  • Hiroyuki Deguchi, Taro Watanabe, Yusuke Matsui, Masao Utiyama, Hideki Tanaka and Eiichiro Sumita. 2023. Subset Retrieval Nearest Neighbor Machine Translation. ACL 2023.

  • Hidetaka Kamigaito, Katsuhiko Hayashi and Taro Watanabe. 2023. Table and Image Generation for Investigating Knowledge of Entities in Pretrained Vision and Language Models. ACL 2023.

  • Ying Zhang, Hidetaka Kamigaito and Manabu Okumura. 2023. Bidirectional Transformer Reranker for Grammatical Error Correction. ACL 2023 Findings.

  • Miyu Oba, Tatsuki Kuribayashi, Hiroki Ouchi and Taro Watanabe. 2023. Second Language Acquisition of Neural Language Models. ACL 2023 Findings.

  • Aru Maekawa, Hidetaka Kamigaito, Kotaro Funakoshi and Manabu Okumura. 2023. Generative Replay Inspired by Hippocampal Memory Indexing for Continual Language Learning. EACL 2023.

  • Jingun Kwon, Hidetaka Kamigaito, Young-In Song and Manabu Okumura. 2023. Hierarchical Label Generation for Text Classification.

  • Jingun Kwon, Hidetaka Kamigaito and Manabu Okumura. 2023. Abstractive Document Summarization with Summary-length Prediction. EACL 2023 Findings.

  • Ukyo Honda, Taro Watanabe and Yuji Matsumoto. 2023. Switching to Discriminative Image Captioning by Relieving a Bottleneck of Reinforcement Learning. WACV 2023.

  • Francisco Casacuberta, George Foster, Guoping Huang, Philipp Koehn, Geza Kovacs, Lemao Liu, Shuming Shi, Taro Watanabe and Chengqing Zong. 2022. Findings of the Word-Level AutoCompletion Shared Task in WMT 2022. WMT 2022.

  • Hiroyuki Deguchi, Kenji Imamura, Masahiro Kaneko, Yuto Nishida, Yusuke Sakai, Justin Vasselli, Huy Hien Vu and Taro Watanabe. 2022. NAIST-NICT-TIT WMT22 General MT Task Submission. WMT 2022.

  • Huayang Li, Deng Cai, Jin Xu and Taro Watanabe. 2022. N-gram Is Back: Residual Learning of Neural Text Generation with n-gram Language Model. EMNLP 2022 Findings.

  • Jungmin Choi, Ukyo Honda, Taro Watanabe, Hiroki Ouchi and Kentaro Inui. 2022. Law retrieval with supervised contrastive learning using the hierarchical structure of law. PACLIC 36.

  • Shuhei Kurita, Hiroki Ouchi, Kentaro Inui and Satoshi Sekine. 2022. Iterative Span Selection: Self-Emergence of Resolving Orders in Semantic Role Labeling. COLING 2022.

  • Zhi Qu and Taro Watanabe. 2022. Adapting to Non-Centered Languages for Zero-shot Multilingual Translation. COLING 2022.

  • Shiki Sato, Reina Akama, Hiroki Ouchi, Ryoko Tokuhisa, Jun Suzuki and Kentaro Inui. 2022. N-best Response-based Analysis of Contradiction-awareness in Neural Response Generation Models. SIGDIAL 2022.

  • Masao Ideuchi, Masatoshi Tsuchiya, Yiran Wang and Masao Utiyama. 2022. NICTmed at the NCTIR-16 Real-MedNLP Task. NTCIR-16.

  • Hidetaka Kamigaito and Katsuhiko Hayashi. 2022. Comprehensive Analysis of Negative Sampling in Knowledge Graph Representation Learning. ICML 2022.

  • Jiannan Xiang, Huayang Li, Defu Lian, Guoping Huang, Taro Watanabe and Lemao Liu. 2022. Visualizing the Relationship Between Encoded Linguistic Information and Task Performance. ACL 2022 Findings.

  • Zuchao Li, Yiran Wang, Masao Utiyama, Eiichiro Sumita, Hai Zhao and Taro Watanabe. 2022. What Works and Doesn’t Work, A Deep Decoder for Neural Machine Translation. ACL 2022 Findings.

  • Yushi Hirose, Masashi Shimbo and Taro Watanabe. 2021. Transductive Data Augmentation with Relational Path Rule Mining for Knowledge Graph Embedding. 2021 IEEE International Conference on Big Knowledge (ICBK).

  • Yuki Yamamoto, Yuji Matsumoto and Taro Watanabe. 2021. Dependency Patterns of Complex Sentences and Semantic Disambiguation for Abstract Meaning Representation Parsing. *SEM 2021.

  • Yiran Wang, Hiroyuki Shindo, Yuji Matsumoto and Taro Watanabe. 2021. Nested Named Entity Recognition via Explicitly Excluding the Influence of the Best Path. ACL-IJCNLP 2021.

  • Wei Bi, Huayang Li and Jiacheng Huang. 2021. Data Augmentation for Text Generation Without Any Augmented Data. ACL-IJCNLP 2021.

  • Deng Cai, Yan Wang, Huayang Li, Wai Lam and Lemao Liu. 2021. Neural Machine Translation with Monolingual Translation Memory. ACL-IJCNLP 2021.

  • Huayang Li, Lemao Liu, Guoping Huang and Shuming Shi. 2021. GWLAN: General Word-Level AutocompletioN for Computer-Aided Translation. ACL-IJCNLP 2021.

  • Yiran Wang, Hiroyuki Shindo, Yuji Matsumoto and Taro Watanabe. 2021. Structured Refinement for Sequential Labeling. ACL-IJCNLP 2021 Findings.

  • Jiannan Xiang, Yahui Liu, Deng Cai, Huayang Li, Defu Lian and Lemao Liu. 2021. Assessing Dialogue Systems with Distribution Distances. ACL-IJCNLP 2021 Findings.

  • Shohei Higashiyama, Masao Utiyama, Taro Watanabe and Eiichiro Sumita. 2021. User-Generated Text Corpus for Evaluating Japanese Morphological Analysis and Lexical Normalization. NAACL-HLT 2021.

  • Ukyo Honda, Yoshitaka Ushiku, Atsushi Hashimoto, Taro Watanabe and Yuji Matsumoto. 2021. Removing Word-Level Spurious Alignment between Images and Pseudo-Captions in Unsupervised Image Captioning. EACL 2021.

  • Vu Tran, Van-Hien Tran, Phuong Minh Nguyen, Chau Minh Nguyen, Ken Satoh, Yuji Matsumoto and Minh Le Nguyen. 2021. CovRelex: A COVID-19 Retrieval System with Relation Extraction. EACL 2021: Demo Track.

  • Yuya Sawada, Takashi Wada, Takayoshi Shibahara, Hiroki Teranishi, Shuhei Kondo, Hiroyuki Shindo, Taro Watanabe and Yuji Matsumoto. 2020. Coordination Boundary Identification without Labeled Data for Compound Terms Disambiguation. COLING 2020.

  • Ikuya Yamada, Akari Asai, Hiroyuki Shindo, Hideaki Takeda and Yuji Matsumoto. 2020. LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attention. EMNLP 2020.

Workshops

  • Adam Nohejl, Akio Hayakawa, Yusuke Ide and Taro Watanabe. 2024. Difficult for Whom? A study of Japanese Lexical Complexity. The Third Workshop on Text Simplification, Accessibility and Readability (TSAR 2024) (to appear).

  • Yusuke Sakai, Adam Nohejl, Jiangnan Hang, Hidetaka Kamigaito and Taro Watanabe. 2024. Toward the Evaluation of Large Language Models Considering Score Variance across Instruction Templates. The BlackboxNLP Workshop (BlackboxNLP 2024) (to appear).

  • Ayuki Katayama, Yusuke Sakai, Shohei Higashiyama, Hiroki Ouchi, Ayano Takeuchi, Ryo Bando, Yuta Hashimoto, Toshinobu Ogiso and Taro Watanabe. 2024. Evaluating Language Models in Location Referring Expression Extraction from Early Modern and Contemporary Japanese Texts. The 4th International Workshop on Natural Language Processing for Digital Humanities (NLP4DH 2024) (to appear).

  • Yuji Oshima, Hiroyuki Shindo, Hiroki Teranishi, Hiroki Ouchi and Taro Watanabe. 2024. Synthetic Context with LLM for Entity Linking from Scientific Tables. SDProc 2024.

  • Xincan Feng, Hidetaka Kamigaito, Katsuhiko Hayashi and Taro Watanabe. 2024. Unified Interpretation of Smoothing Methods for Negative Sampling Loss Functions in Knowledge Graph Embedding. Repl4NLP 2024.

  • Ken Nishida, Kojiro Machi, Kazuma Onishi, Katsuhiko Hayashi and Hidetaka Kamigaito. 2024. Multi-label Learning with Random Circular Vectors. Repl4NLP 2024.

  • Kosuke Doi, Yuka Ko, Mana Makinae, Katsuhito Sudoh and Satoshi Nakamura. 2024. Word Order in English-Japanese Simultaneous Interpretation: Analyses and Evaluation using Chunk-wise Monotonic Translation. IWSLT 2024.

  • Yuka Ko, Ryo Fukuda, Yuta Nishikawa, Yasumasa Kano, Tomoya Yanagita, Kosuke Doi, Mana Makinae, Haotian Tan, Makoto Sakai, Sakriani Sakti, Katsuhito Sudoh and Satoshi Nakamura. 2024. NAIST Simultaneous Speech Translation System for IWSLT 2024. IWSLT 2024.

  • Yuhi Matogawa, Yusuke Sakai, Taro Watanabe and Chihiro Taguchi. 2024. Japanese Rule-based Grapheme-to-phoneme Conversion System and Multilingual Named Entity Dataset with International Phonetic Alphabet. SIGMORPHON 2024.

  • Justin Vasselli, Arturo Martínez Peguero, Junehwan Sung and Taro Watanabe. 2024. Applying Linguistic Expertise to LLMs for Educational Material Development in Indigenous Languages. AmericasNLP 2024.

  • Matthew Shardlow, Fernando Alva-Manchego, Riza Batista-Navarro, Stefan Bott, Saul Calderon Ramirez, Rémi Cardon, Thomas François, Akio Hayakawa, Andrea Horbach, Anna Huelsing, Yusuke Ide, Joseph Marvin Imperial, Adam Nohejl, Kai North, Laura Occhipinti, Nelson Peréz Rojas, Nishat Raihan, Tharindu Ranasinghe, Martin Solis Salazar, Sanja Stajner, Marcos Zampieri and Horacio Saggion. 2024. The BEA 2024 Shared Task on the Multilingual Lexical Simplification Pipeline. BEA 2024.

  • Kosuke Doi, Katsuhito Sudoh and Satoshi Nakamura. 2024. Automated Essay Scoring Using Grammatical Variety and Errors with Multi-Task Learning and Item Response Theory. BEA 2024.

  • Arturo Martinez Peguero. 2024. Change My Frame: Reframing in the Wild in r/ChangeMyView. LatinXinAI (to appear).

  • Matthew Shardlow, Fernando Alva-Manchego, Riza Batista-Navarro, Stefan Bott, Saul Calderon Ramirez, Rémi Cardon, Thomas François, Akio Hayakawa, Andrea Horbach, Anna Hülsing, Yusuke Ide, Joseph Marvin Imperial, Adam Nohejl, Kai North, Laura Occhipinti, Nelson Peréz Rojas, Nishat Raihan, Tharindu Ranasinghe, Martin Solis Salazar, Marcos Zampieri and Horacio Saggion. 2024. An Extensible Massively Multilingual Lexical Simplification Pipeline Dataset using the MultiLS Framework. 3rd Workshop on Tools and Resources for People with REAding DIfficulties (READI).

  • Yuto Nishida, Makoto Morishita, Hidetaka Kamigaito and Taro Watanabe. 2024. Generating Diverse Translation with Perturbed kNN-MT. EACL 2024 Student Research Workshop.

  • Miyu Oba, Akari Haga, Akiyo Fukatsu and Yohei Oseki. 2023. BabyLM Challenge: Curriculum learning based on sentence complexity approximating language acquisition. the BabyLM Challenge at the 27th Conference on Computational Natural Language Learning.

  • Justin Vasselli, Christopher Vasselli, Adam Nohejl and Taro Watanabe. 2023. NAISTeacher: A Prompt and Rerank Approach to Generating Teacher Utterances in Educational Dialogues. 18th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2023). 1st Rank in BEA 2023 Shared Task

  • Justin Vasselli and Taro Watanabe. 2023. A Closer Look at k-Nearest Neighbors Grammatical Error Correction. 18th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2023).

  • Yusuke Ide, Masato Mita, Adam Nohejl, Hiroki Ouchi, and Taro Watanabe. 2023. Japanese Lexical Complexity for Non-Native Readers: a New Dataset. 18th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2023).

  • Akio Hayakawa, Tomoyuki Kajiwara, Hiroki Ouchi and Taro Watanabe. 2022. JADES: New Text Simplification Dataset in Japanese Targeted at Non-Native Speakers. Workshop on Text Simplification, Accessibility, and Readability (TSAR-2022).

  • Xincan Feng, Zhi Qu, Yuchang Cheng, Taro Watanabe and Nobuhiro Yugami. 2022. Sharing Parameter by Conjugation for Knowledge Graph Embeddings in Complex Space. TextGraphs-16.

  • Chihiro Taguchi, Sei Iwata and Taro Watanabe. 2022. Universal Dependencies Treebank for Tatar: Incorporating Intra-Word Code-Switching Information. Workshop on Resources and Technologies for Indigenous, Endangered and Lesser-resourced Languages (EURALI-2022).

  • Van-Hien Tran, Hiroki Ouchi, Taro Watanabe and Yuji Matsumoto. 2022. Improving Discriminative Learning for Zero-Shot Relation Extraction. 1st Workshop on Semiparametric Methods in NLP: Decoupling Logic from Knowledge (SpaNLP).

  • Shohei Higashiyama, Masao Utiyama, Taro Watanabe and Eiichiro Sumita. 2021. A Text Editing Approach to Joint Japanese Word Segmentation, POS Tagging, and Lexical Normalization. Seventh Workshop on Noisy User-generated Text (W-NUT 2021). Best Paper Award

  • Yushi Hirose, Shimbo Masashi and Taro Watanabe. 2021. Transductive Data Augmentation with Relational Path Rule Induction for Knowledge Graph Embedding. International Workshop on Knowledge Graph: Heterogeneous Graph Deep Learning and Applications.

  • Shintaro Harada and Taro Watanabe. 2021. Neural Machine Translation with Synchronous Latent Phrase Structure. ACL-IJCNLP 2021 Student Research Workshop.

  • Sei Iwata, Taro Watanabe and Masaaki Nagata. 2021. Zero Pronouns Identification based on Span prediction. ACL-IJCNLP 2021 Student Research Workshop.

  • Hiroyuki Deguchi, Akihiro Tamura and Takashi Ninomiya. 2021. Synchronous Syntactic Attention for Transformer Neural Machine Translation. ACL-IJCNLP 2021 Student Research Workshop.

  • Chihiro Taguchi, Yusuke Sakai and Taro Watanabe. 2021. Transliteration for Low-Resource Code-Switching Texts: Building an Automatic Cyrillic-to-Latin Converter for Tatar. Fifth Workshop on Computational Approaches to Linguistic Code-Switching (CALCS 2021).

  • Takayoshi Shibahara, Ikuya Yamada, Noriki Nishida, Shanshan Liu, Kouji Kozaki, Taro Watanabe and Yuji Matsumoto. 2020. Preliminary Experiments of Span-based Distant Supervision for Biomedical NER. Fourth International Workshop on SCIentific DOCument Analysis (SCIDOCA 2020).

  • Yuya Sawada, Hiroki Teranishi and Yuji Matsumoto. 2020. Coordination Identification for Composite Named Entity Normalization. Fourth International Workshop on SCIentific DOCument Analysis (SCIDOCA 2020).

  • Hien Van Tran, Phuong Minh Nguyen, Chau Minh Nguyen, Ken Satoh, Yuji Matsumoto and Minh Le Nguyen. 2020. CovRelex: A COVID-19 Retrieval System with Relation Extraction. Fourth International Workshop on SCIentific DOCument Analysis (SCIDOCA 2020).

  • Shanshan Liu, Matsunori Uenuma, Hiroyuki Shindo and Yuji Matsumoto. 2020. Extraction of the Material Synthesis Procedure. Fourth International Workshop on SCIentific DOCument Analysis (SCIDOCA 2020).

Presentations at conferences/SIGs

  • 蒔苗 茉那, 坂井 優介, 上垣外 英剛, 渡辺 太郎. 2024. Simul-MuST-C：大規模言語モデルによる語順の単調性に着目した同時音声翻訳用コーパスの構築. IPSJ SIG NL (in Japanese). Young Researcher Award

  • 五藤 巧, 出口 祥之, 上垣外 英剛, 渡辺 太郎. 2024. k近傍事例を用いたニューラルモデルの予測における定量的な解釈. IPSJ SIG NL (in Japanese).

  • 井手 佑翼, 西田 悠人, 大羽 未悠, 坂井 優介, Justin Vasselli, 上垣外 英剛, 渡辺 太郎. 2024. Investigating Acceptability Judgment Methods Suitable for Large Language Models. IPSJ SIG NL (in Japanese). Young Researcher Award

  • 出口祥之, 坂井優介, 上垣外英剛, 渡辺太郎. 2024. 疑似参照訳文ベクトルの重心に基づく高速なニューラル最小ベイズリスク復号. NLP 2024. SmartESG (Cierpa & Company) Award

  • 平野颯, 上垣外英剛, 渡辺太郎. 2024. 深層学習モデルにおける言語特徴分布に関する研究. NLP 2024.

  • 大嶋悠司, 進藤裕之, 寺西裕紀, 大内啓樹, 渡辺太郎. 2024. LLM による合成文脈データを用いた表のエンティティリンキング. NLP 2024.

  • 大南英理, 栗田修平, 宮西大樹, 渡辺太郎. 2024. JDocQA: 図表を含む日本語文書質問応答データセットによる大規模言語モデルチューニング. NLP 2024. Young Researcher Award PKSHA Technology Award Money Forward Award

  • 郷原聖士, 上垣外英剛, 渡辺太郎. 2024. LLM はユーザーに適したテキストの難易度を暗黙的に考慮しているのか？. NLP 2024.

  • 山本和太郎, 大友寛之, 大内啓樹, 東山翔平, 寺西裕紀, 進藤裕之, 渡辺太郎. 2024. 移動軌跡解析：文章中の人物の地理的な移動を読み取る. NLP 2024.

  • 林和樹, 坂井優介, 上垣外英剛, 林克彦, 渡辺太郎. 2024. Large-scale Vision Language Modelによる芸術作品に対する説明の生成. NLP 2024.

  • 齊藤成輝, 林和樹, 井手佑翼, 坂井優介, 鈴木刀磨, 郷原聖士, 大西雄真, 上垣外英剛, 林克彦, 渡辺太郎. 2024. Vision Language Modelが持つ画像批評能力の評価手法の提案. NLP 2024.

  • 中谷響, 寺西裕紀, 東山翔平, 大内啓樹, 渡辺太郎. 2024. メンション文脈とエントリ属性を考慮した Transformer Bi-Encoder によるジオコーディング. NLP 2024.

  • 東山翔平, 大内啓樹, 寺西裕紀, 大友寛之, 井手佑翼, 山本和太郎, 進藤裕之, 渡辺太郎. 2024. 日本語旅行記ジオパージングデータセットATD-MCL. NLP 2024. Committee Special Award

  • 辻本陵, 大内啓樹, 上垣外英剛, 渡辺太郎. 2024. 衛星画像の時系列変化説明に向けたLVLMの比較. NLP 2024.

  • 浅野輝, 米谷竜, 関井大気, 大内啓樹. 2024. Text2Traj2Text: 大規模言語モデルを活用した段階的データ生成に基づく人物移動軌跡の言語化. NLP 2024.

  • 四條光, 進藤裕之, 渡辺太郎. 2024. 画像ベースとテキストベースのモデルを用いた表の構造解析の性能検証. NLP 2024.

  • Junehwan Sung, 上垣外英剛, 渡辺太郎. 2024. Exploring Metalinguistic Awareness in Pre-trained Language Models through the International Linguistics Olympiad Challenges. NLP 2024.

  • 富村勇貴, 上垣外英剛, 渡辺太郎. 2024. 固有名詞置換による共参照解析データセットの拡張. NLP 2024.

  • 五藤巧, 渡辺太郎. 2024. 文法誤り訂正における参照なし評価尺度を用いた分析的評価法. NLP 2024. Young Researcher Award

  • 芳賀あかり, 菅原朔, 深津聡世, 大羽未悠, 大内啓樹, 渡辺太郎, 大関洋平. 2024. 小規模言語モデルによる子供の過剰一般化のモデリング. NLP 2024.

  • 坂井優介, 上垣外英剛, 渡辺太郎. 2024. Multilingual CommonsenseQA. NLP 2024.

  • Justin Vasselli, Taro Watanabe. 2024. Adversarial Evaluation of Dialogue System Metrics. NLP 2024.

  • 大羽未悠, 大関洋平, 深津聡世, 芳賀あかり, 大内啓樹, 渡辺太郎, 菅原朔. 2024. 言語モデルの文法知識評価における間接肯定証拠の分析. NLP 2024.

  • 橋本航, 上垣外英剛, 渡辺太郎. 2024. データ拡張による固有表現抽出の不確実性推定. NLP 2024.

  • 澤田悠冶, 安井雄一郎, 大内啓樹, 渡辺太郎, 石井昌之, 石原祥太郎, 山田剛, 進藤裕之. 2024. 日経企業 ID リンキングのための類似度ベース EL システムの構築と分析. NLP 2024.

  • 前川在, 平尾努, 上垣外英剛, 奥村学. 2024. 大規模言語モデルによるシフト還元修辞構造解析の模倣. NLP 2024.

  • 帖佐克己, 上垣外英剛, 渡辺太郎. 2024. 翻訳文の部分構造を制約とした機械翻訳. NLP 2024. Young Researcher Award

  • kNN言語モデルは低頻度語の予測に役立つか？. 2024. 西田悠人, 森下睦, 出口祥之, 上垣外英剛, 渡辺太郎. NLP 2024. Young Researcher Award

  • 白井 尚登, 上垣外 英剛, 渡辺 太郎. 2024. Scalar Mixing Weightsを用いた生成タスクにおける視覚と言語の情報を事前学習したモデルの分析. IPSJ SIG NL (in Japanese).

  • 鈴木 刀磨, 坂井 優介, 上垣外 英剛, 渡辺 太郎. 2024. 大規模言語モデルにおけるタスク特有の表層表現に起因する脆弱性の調査. IPSJ SIG NL (in Japanese).

  • 武内 樹治, 大内啓樹, 東山翔平. 2023. 歴史災害史料からの自動地名抽出に向けた自然言語処理システムの性能評価. 人文科学とコンピュータシンポジウム2023.

  • 西田 拳, 林 克彦, 町 光二郎, 上垣外 英剛. 2023. ランダム巡回ベクトルを用いたマルチラベル学習. IPSJ SIG NL (in Japanese).

  • 片山 歩希, 東山 翔平, 大内 啓樹, 渡辺 太郎. 2023. 歴史的日本語資料を対象とした場所参照表現抽出―「おくのほそ道」を例として―. IPSJ SIG NL (in Japanese).

  • 坂井 優介, ノヘイル アダム, 上垣外 英剛, 渡辺 太郎. 2023. 大規模言語モデルの統一評価に向けた指示テンプレートの提案及びその評価結果の考察. IPSJ SIG NL (in Japanese). Excellent Research Award

  • 坂井 優介, 上垣外 英剛, 林 克彦, 渡辺 太郎. 2023. 未知の知識に対する事前学習済み言語モデルが持つ推論能力の調査. IPSJ SIG NL (in Japanese). Excellent Research Award

  • 山本 和太郎, 東山 翔平, 大内 啓樹, 大友 寛之, 井手 佑翼, 進藤 裕之, 渡辺 太郎. 2023. 移動軌跡可視化のための旅行記への訪問順序アノテーション. JSAI 2023 (in Japanese).

  • 大嶋 悠司, 進藤 裕之, 渡辺 太郎. 2023. 引用文献に着目した情報科学論文からのデータセットの抽出. IPSJ SIG NL (in Japanese).

  • Yuya Sawada, Hiroki Teranishi, Hiroki Ouchi, Yuji Matsumoto and Taro Watanabe. 2023. Estimating Named Entity Label Representation for Generative Low-Resource NER. IPSJ SIG NL (in Japanese).

  • 廣瀬惟歩, 渡辺太郎. 2023. 日英翻訳を対象としたイディオム表現の評価指標の提案. NLP 2023.

  • 五藤巧, 渡辺太郎. 2023. 訂正文の流暢性向上を目的とした系列タグ付け文法誤り訂正器の強化学習手法. NLP 2023.

  • 西田悠人, 森下睦, 上垣外英剛, 渡辺太郎. 2023. 摂動を加えたkNN機械翻訳による多様な翻訳候補の生成. NLP 2023.

  • 出口祥之, 渡辺太郎, 松井勇佑, 内山将夫, 田中英輝, 隅田英一郎. 2023. 近傍文検索を用いたサブセットkNNニューラル機械翻訳. NLP 2023.

  • 大羽未悠, 栗林樹生, 大内啓樹, 渡辺太郎. 2023. 言語モデルの第二言語獲得. NLP 2023. Young Researcher Award

  • Xincan Feng, 上垣外英剛, 林克彦, 渡辺太郎. 2023. 知識グラフ補完のためのモデル予測に基づくサブサンプリング. NLP 2023.

  • 星野智紀, 上垣外英剛, 渡辺太郎. 2023. 忠実性向上のためにn-gramの抽出性を報酬とする強化学習を用いる抽象型要約. NLP 2023.

  • 亀井遼平, 横井祥, 仲村祐希, 渡辺太郎, 乾健太郎. 2023. 柔らかいジャンプ付き編集距離に向けて. NLP 2023.

  • 張培楠, 坂井優介, 三田雅人, 大内啓樹, 渡辺太郎. 2023. AdGLUE: 広告言語理解ベンチマーク. NLP 2023.

  • 芝原隆善, 山田育矢, 西田典起, 寺西裕紀, 大内啓樹, 古崎晃司, 渡辺太郎, 松本裕治. 2023. エンティティの階層的分類体系を用いた遠距離教師あり固有表現抽出. NLP 2023.

  • 前川在, 小林尚輝, 平尾努, 上垣外英剛, 奥村学. 2023. 逆翻訳を利用したデータ拡張による文間の修辞構造解析の改善. NLP 2023.

  • 的川雄飛, 坂井優介, 平野颯, 澤田悠冶, 大内啓樹, 渡辺太郎. 2023. ルールベースG2Pによる多言語固有表現の国際音声記号表記付きデータセットの構築. NLP 2023.

  • 芳賀あかり, 平尾努, 帖佐克己, 本多右京, 出口祥之, 渡辺太郎. 2023. 画像キャプショニングのための制約語の抽出法. NLP 2023.

  • 白井尚登, 上垣外英剛, 渡辺太郎. 2023. エッジプロービングを用いた事前学習済みの視覚と言語に基づくモデルにおける言語知識の分析. NLP 2023.

  • 久本空海, 西尾悟, 井口奏大, 古川泰人, 大友寛之, 東山翔平, 大内啓樹. 2023. 場所参照表現と位置情報を紐付けるジオコーディングの概観と発展に向けての考察. NLP 2023.

  • 村上聡一朗, 菊田洸, 張培楠, 上垣外英剛, 高村大也, 奥村学. 2023. 原文の書き換えによる広告文生成. NLP 2023.

  • 川畑輝, 菅原朔. 2023. 読解問題における論理推論の一貫性評価. NLP 2023. Young Researcher Award

  • 大内啓樹, 進藤裕之, 若宮翔子, 松田裕貴, 井之上直也, 東山翔平, 中村哲, 渡辺太郎. 2023. 地球の歩き方旅行記データセット. NLP 2023.

  • 大友寛之, 東山翔平, 大内啓樹, 山本和太郎, 井手佑翼, 進藤裕之, 渡辺太郎. 2023. 旅行記中の場所に対する訪問状態の予測. NLP 2023.

  • 齋藤玲, 大内啓樹, 羽鳥康裕, 邑本俊亮, 杉浦元亮, 塩入諭, 柴山明寛. 2023. 震災アーカイブと震災アーカイブwebに関する概念モデルの作成. NLP 2023.

  • 上垣外英剛, 林克彦, 渡辺太郎. 2023. 視覚と言語の融合モデルにおける知識の振る舞いを調査するための表と画像の生成タスクの提案及びその調査結果. NLP 2023. Committee Special Award

  • Miyu Oba, Tatsuki Kuribayashi, Hiroki Ouchi and Taro Watanabe. 2022. 言語モデルの第二言語獲得効率. IPSJ SIG NL (in Japanese). Excellent Research Award

  • Yuhi Matogawa. 2022. Classification of /j/ and /w/ in donor languages and notations of /CjV/ and /CwV/ in Japanese. IEICE SIG TL (in Japanese).

  • Yusuke Ide, Hiroyuki Deguchi, Takumi Goto, Armin Sarhangzadeh and Taro Watanabe. 2022. Studies of the Impact of Subsequent Context Information in Grammatical Error Correction. IPSJ SIG NL (in Japanese).

  • Takumi Goto, Ryo Nagata and Masato Mita. 2022. Exploring Human-judged and Automatically-induced Correction Difficulty for Grammatical Error Correction. IPSJ SIG NL (in Japanese). Young Researcher Award

  • Jungmin Choi, Ukyo Honda, Taro Watanabe, Kentaro Inui. 2022. Law Retrieval With Supervised Contrastive Learning Using the Hierarchical Structure of Law. JSAI 2022 (in Japanese). Annual Conference Award

  • Yuto Harada and Taro Watanabe. 2022. 入れ子型固有表現に対する変分情報ボトルネック法の適用. NLP 2022.

  • Ukyo Honda, Taro Watanabe and Yuji Matsumoto. 2022. 強化学習における画像キャプションの低識別性問題とLong-Tail分類手法を用いた対処. NLP 2022. Grand Pize

  • Takayoshi Shibahara, Hiroki Ouchi, Ikuya Yamada, Noriki Nishida, Hiroki Teranishi, Kouji Kozaki, Taro Watanabe and Yuji Matsumoto. 2022. ユーザの興味があるカテゴリに応じたNER システム構築フレームワーク. NLP 2022.

  • Akihiko Kato, Shuhei Kondo, Hiroyuki Shindo and Taro Watanabe. 2022. 材料科学論文の表の意味解釈データセットの構築. NLP 2022.

  • Akio Hayakawa, Hiroki Ouchi, Tomoyuki Kajiwara and Taro Watanabe. 2022. テキスト平易化における自動評価指標のメタ評価の検討. NLP 2022.

  • Yusuke Oda and Yuya Sawada. 2022. 制約抽出のための対訳コーパスを用いた半教師ありクロスリンガル用語推定. NLP 2022.

  • Hayate Hirano, Hiroki Ouchi and Taro Watanabe. 2022. 多言語機械翻訳への言語類型論特徴の導入. NLP 2022.

  • Yusuke Sakai, Chihiro Taguchi and Taro Watanabe. 2022. タタール語におけるサブワード単位の言語識別を加味したキリル文字からラテン文字への翻字システムの開発. NLP 2022.

  • Shintaro Harada, Taro Watanabe and Hiroki Ouchi. 2022. 雑音のある通信路モデルを用いた句構造解析. NLP 2022.

  • Hiroyuki Otomo, Hiroki Ouchi, Tomoki Hoshino, Yusuke Ide and Taro Watanabe. 2022. 訪問場所表現グラウンディングのためのアノテーション. NLP 2022.

  • Chihiro Taguchi. 2021. Mermaid construction in Tatar. The 162nd Meeting of the Linguistic Society of Japan.

  • Yuya Sawada, Hiroki Teranichi, Yuji Matsumoto and Taro Watanabe. 2021. 並列構造解析に基づく複合化された固有表現の曖昧性解消. NLP 2021.

  • Chihiro Taguchi and Taro Watanabe. 2021. So-Called “Prepositions” in Somali are Not Prepositions: A Linguistic Approach for Somali POS Tagging. NLP 2021.

  • Takuro Niitsuma and Taro Watanabe. 2021. 文表現の摂動正規化: 事前学習済みモデルのDebias手法. NLP 2021.

  • Yasuhiro Yamaguchi, Hiroyuki Shindo and Taro Watanabe. 2021. ラベルの不均衡を考慮したEnd-to-End情報抽出モデルの学習. NLP 2021.

  • Hayate Hirano, Ko Nomura, Hiroyuki Shindo and Taro Watanabe. 2021. 遺伝子二重欠失研究のための関連論文検索手法. NLP 2021.

  • Yushi Hirose, Masashi Shimbo and Taro Watanabe. 2021. 知識グラフエンベディングのためのリレーションパスルールによるトランスダクティブデータ拡張. NLP 2021.

  • Sei Iwata, Taro Watanabe and Masaaki Nagata. 2021. 質問応答に基づく日本語ゼロ代名詞同定. NLP 2021.

  • Yusuke Sakai, Taro Watanabe and Atsuchi Fujita. 2021. 知識グラフ埋め込みを用いたニューラル機械翻訳におけるエンティティ表現の改良. NLP 2021.

  • Shintaro Harada and Taro Watanabe. 2021. 教師なし同期的句構造を用いた機械翻訳. NLP 2021.

  • Ukyo Honda, Yoshitaka Ushiku, Atsushi Hashimoto, Taro Watanabe and Yuji Matsumoto. 2021. 画像と単語の不一致を考慮した疑似教師ありキャプション生成. NLP 2021. Young Researcher Award

  • Takayoshi Shibahara, Ikuya Yamada, Noriki Nishida, Shanshan Liu, Kouji Kozaki, Taro Watanabe and Yuji Matsumoto. 2021. 入れ子になっている固有表現に対する Distant Supervision. NLP 2021.

  • Yoshitaka Sato, Takashi Wada, Taro Watanabe and Yuji Matsumoto. 2020. Pseudo Data Generation for Grammatical Error Correction Considering the Native Language of English Learners. IPSJ SIG NL (in Japanese). Young Researcher Award

  • Yuki Yamamoto, Yuji Matsumoto and Taro Watanabe. 2020. Complex Sentence Pattern Lexicon for AMR and Experiments on Semantic Ambiguity Resolution. IPSJ SIG NL (in Japanese).

  • Chihiro Taguchi. 2020. Raising to quirky subject in Tatar. The 161st Meeting of the Linguistic Society of Japan.

Others (articles, talks etc.)

  • 二宮 崇, 出口 祥之, 内山 将夫, 田村 晃裕, 隅田 英一郎. 2021. ニューラル機械翻訳のためのバイリンガルサブワード分割の研究. Japio YEAR BOOK 2021.

  • Taro Watanabe. 2020. Book Review: Neural Machine Translation by Philipp Koehn. AAMT Journal (in Japanese).