We will present the following papers at EMNLP 2024(2024/11) †

• Yin Jou Huang, Rafik Hadfi: How Personality Traits Influence Negotiation Outcomes? A Simulation based on Large Language Models (Findings)
• Junfeng Jiang, Fei Cheng, Akiko Aizawa: Improving Referring Ability for Biomedical Language Models (Findings)

Zhuoyuan Mao who got his Ph.D. degree last fiscal year received the AAMT Nagao Award Student Encouragement Award for his following doctoral thesis (2024/5). †

• Breaking Language Barriers: Enhancing Multilingual Representation for Sentence Alignment and Translation

We will present the following papers at ACL 2024 (2024/8) . †

• Sirou Chen, Sakiko Yahata, Shuichiro Shimizu, Zhengdong Yang, Yihang Li, Chenhui Chu, Sadao Kurohashi:
  MELD-ST: An Emotion-aware Speech Translation Dataset (Findings)
• Yahan Yu, Duzhen Zhang, Xiuyi Chen, Chenhui Chu:
  Flexible Weight Tuning and Weight Fusion Strategies for Continual Named Entity Recognition (Findings)
• Duzhen Zhang, Yahan Yu, Chenxing Li, Jiahua Dong, Dan Su, Chenhui Chu, Dong Yu:
  MM-LLMs: Recent Advances in MultiModal Large Language Models (Findings)
• Zhen Wan, Yating Zhang, Yexiang Wang, Fei Cheng, Sadao Kurohashi:
  Reformulating Domain Adaptation of Large Language Models as Adapt-Retrieve-Revise: A Case Study on Chinese Legal Domain (Findings)

We will hold a briefing session (2024/5/11) †

• As part of the admission orientation of the Intelligence Science and Technology Course held on 11 May, 2024, our lab will have an onsite briefing session after the course-wide session. We plan to hold two briefing sessions from 15:00 and 16:00, respectively.

The following paper received the FY2023 best paper award of the Journal of Natural Language Processing (2024/3) †

• Kazumasa Omura, Daisuke Kawahara, and Sadao Kurohashi:
  Building a Commonsense Inference Dataset based on Basic Events and its Application

We will present the following papers at LREC-COLING 2024 (2024/5). †

• Taishi Chika, Taro Okahisa, Takashi Kodama, Yin Jou Huang, Yugo Murawaki and Sadao Kurohashi:
  Domain Transferable Semantic Frames for Expert Interview Dialogues
• Yikun Sun, Zhen Wan, Nobuhiro Ueda, Sakiko Yahata, Fei Cheng, Chenhui Chu and Sadao Kurohashi:
  Rapidly Developing High-quality Instruction Data and Evaluation Benchmark for Large Language Models with Minimal Human Effort: A Case Study on Japanese
• Norizo Sakaguchi, Yugo Murawaki, Chenhui Chu and Sadao Kurohashi:
  Identifying Source Language Expressions for Pre-editing in Machine Translation
• Nobuhiro Ueda, Hideko Habe, Yoko Matsui, Akishige Yuguchi, Seiya Kawano, Yasutomo Kawanishi, Sadao Kurohashi and Koichiro Yoshino: J-CRe3:
  A Japanese Conversation Dataset for Real-world Reference Resolution
• Hao Wang, Tang Li, Chenhui Chu, Rui Wang and Pinpin Zhu:
  Towards Human-Like Machine Comprehension: Few-Shot Relational Learning in Visually-Rich Documents
• Rikito Takahashi, Hirokazu Kiyomaru, Chenhui Chu and Sadao Kurohashi:
  Abstractive Multi-Video Captioning: Benchmark Dataset Construction and Extensive Evaluation
• Yugo Murawaki:
  Principal Component Analysis as a Sanity Check for Bayesian Phylolinguistic Reconstruction
• Kazumasa Omura, Fei Cheng and Sadao Kurohashi:
  An Empirical Study of Synthetic Data Generation for Implicit Discourse Relation Recognition
• Xiaotian Lu, Jiyi Li, Zhen Wan, Xiaofeng Lin, Koh Takeuchi and Hisashi Kashima:
  Evaluating Saliency Explanations in NLP by Crowdsourcing
• Francois Meyer, Haiyue Song, Abhisek Chakrabarty, Jan Buys, Raj Dabre and Hideki Tanaka:
  NGLUEni: Benchmarking and Adapting Pretrained Language Models for Nguni Languages

Search Engine Infrastructure based on Deep Natural Language Processing †

The essential purpose of information retrieval is not to retrieve just a relevant document but to acquire the information or knowledge in the document. We have been developing a next-generation infrastructure of information retrieval on the basis of the following techniques of deep natural language processing: precise processing based not on words but on predicate-argument structures, identifying the variety of linguistic expressions and providing a bird's-eye view of search results via clustering and interaction.

Machine Translation †

To bring automatic translation by computers to the level of human translation, we have been studying next-generation methodology of machine translation on the basis of text understanding and a large collection of translation examples. We have already accomplished practical translation on the domain of travel conversation, and constructed a translation-aid system that can be used by experts of patent translation.