What's New

The following papers received the excellence award of the 32-th annual meeting of the association for natural language processing (2026/3).

  • Noriki Nishida, Fei Cheng, Yuji Matsumoto: Continual Structuring of Dynamic Unstructured External Knowledge and Its Application to Long-Context RAG

Zhang-kun, Tarutani-kun, and Yu-san received the young researcher award of the 32-th annual meeting of the association for natural language processing with the following papers (2026/3).

  • Zelin Zhang, Hiroki Tarutani, Toshiaki Nakazawa, Fei Cheng, Chenhui Chu: Claim-Wise Interaction Modeling with Hybrid Context and Domain-Adaptive Dictionary for Japanese Patent Retrieval
  • Yahan Yu, Chenhui Chu: Lightweight Progressive LoRA for Multimodal Continual Instruction Tuning

The following papers received the special committee award of the 29-th annual meeting of the association for natural language processing (2026/3).

  • Yang Liu, Masahiro Kaneko, Chenhui Chu: Global Value Alignment in Large Language Models
  • Noriki Nishida, Rumana Ferdous Munne, Shanshan Liu, Narumi Tokunaga, Yuki Yamagata, Fei Cheng, Kouji Kozaki, Yuji Matsumoto: A Module-Wise Analysis of Knowledge Structuring in Graph-Based RAG

Prof. Kurohashi was selected as ACL Fellows 2025.

The following paper won the Best Paper Award in the AAAI 2026 AI Alignment Track.

  • Yang Liu, Masahiro Kaneko, Chenhui Chu: On the Alignment of Large Language Models with Global Human Opinion

We will present the following papers at EACL 2026 (2026/3).

  • Chengzhi Zhong, Fei Cheng, Qianying Liu, Yugo Murawaki, Chenhui Chu, Sadao Kurohashi: Language Lives in Sparse Dimensions: Toward Interpretable and Efficient Multilingual Control for Large Language Models
  • Shanshan Liu, Noriki Nishida, Fei Cheng, Narumi Tokunaga, Rumana Ferdous Munne, Yuki Yamagata, Kouji Kozaki, Takehito Utsuro, Yuji Matsumoto. Better Generalizing to Unseen Concepts: An Evaluation Framework and An LLM-Based Auto-Labeled Pipeline for Biomedical Concept Recognition
  • Jivnesh Sandhan, Fei Cheng, Tushar Sandhan, and Yugo Murawaki. Deterministic Personality Editing of Large Language Models Using Adversarial Conversational History (Findings)

We will present the following paper at AAAI 2026 (2026/1).

  • Yang Liu, Masahiro Kaneko, Chenhui Chu:
    On the Alignment of Large Language Models with Global Human Opinion

The following presentations and roles are scheduled for AACL 2025 (2025/12).

  • Professor Kurohashi will deliver the keynote address.
  • Shimizu, a doctoral student, will chair the Student Research Workshop.
  • We will present the following paper.
    • Kunal Kingkar Das, Manoj Balaji Jagadeeshan, Nallani Chakravartula Sahith, Jivnesh Sandhan, and Pawan Goyal: Still Not There: Can LLMs Outperform Smaller Task-Specific Seq2Seq Models on the Poetry-to-Prose Conversion Task?
    • Wan Jou She, Lis Pereira, Fei Cheng, Sakiko Yahata, Panote Siriaraya, Eiji Aramaki. EmplifAI: a Fine-grained Dataset for Japanese Empathetic Medical Dialogues in 28 Emotion Labels

Research Overview

Language is the most reliable medium of human intellectual activities. Our objective is to establish the technology and academic discipline for handling and understanding language, in a manner that is as close as possible to that of humans, using computers. These include syntactic language analysis, semantic analysis, context analysis, text comprehension, text generation and dictionary systems to develop various application systems for machine translation and information retrieval.

Search Engine Infrastructure based on Deep Natural Language Processing

TSUBAKI.png

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

EBMT.png

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.

Fundamental Studies on Text Understanding

To make computers understand language, it is essential to give computers world knowledge. This was a very hard problem ten years ago, but it has become possible to acquire knowledge from a massive amount of text in virtue of the drastic progress of computing power and network. We have successfully acquired linguistic patterns of predicate-argument structures from automatic parses of 7 billion Japanese sentences crawled from the Web using grid computing machines. By utilizing such knowledge, we study text understanding, i.e., recognizing the relationships between words and phrases in text.

Policy Regarding Acceptance of Students from Outside

Prof. Kurohashi does not supervise new students. Assoc. Prof. Murawaki or Assoc. Prof. Chu will be responsible for supervising their research.

Master course

PhD course

Access