/ Qin Dai / 代　勤

I am a postdoctoral researcher at Natural Language Processing Group (Inui Lab),
Graduate School of Information Sciences, Tohoku University, in Sendai, Japan.

Contact: daiqin[at] ecei.tohoku.ac.jp

Research Interests

• Knowledge acquisition, especially scientific knowledge acquisition
• Deep learning for scientific knowledge discovery
• Universal graph (Text + KB) based reasoning
• Natural language grounding

Education

Graduate School of Information Sciences, Tohoku University, Japan
PhD in Information Sciences (Mar. 2020)
Supervisor: Prof. Kentaro Inui

Journals

• Qin Dai, Naoya Inoue, Paul Reisert, and Kentaro Inui. Leveraging Unannotated Texts for Scientific Relation Extraction.
  IEICE Transactions on Information and Systems, Vol. E101-D, No. 12, pp.3209-3217, December 2018. [paper]
• Qin Dai, Benjamin Heinzerling, Naoya Inoue and Kentaro Inui. Universal Graph based Distantly Supervised Relation Extraction.
  Journal of Natural Language Processing, Vol. 29, No. 4, pp.1138-1164, December 2022. [paper]

International Conference Papers

• Qin Dai, Benjamin Heinzerling and Kentaro Inui. Cross-stitching Text and Knowledge Graph Encoders for Distantly Supervised Relation Extraction.
  In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP2022).[paper][arxiv]
• Qin Dai, Naoya Inoue, Ryo Takahashi and Kentaro Inui. Two Training Strategies for Improving Relation Extraction over Universal Graph.
  In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2021), virtual. [paper][arxiv]
• Qin Dai, Naoya Inoue, Ryo Takahashi and Kentaro Inui. Enhancing Biomedical Relation Extraction with Indirect Evidences.
  In Proceedings of Fourth International Workshop on SCIentific DOCument Analysis (SCIDOCA), November 2020. [Link]
• Qin Dai, Naoya Inoue, Paul Reisert, Takahashi Ryo, and Kentaro Inui. Incorporating chains of reasoningover knowledge graph for distantly supervised biomedical knowledge acquisition.
  In Proceedings of the 33rd Pacific Asia Conference on Language, Information and Computation (PACLIC33), September 2019. [paper]
• Qin Dai, Naoya Inoue, Paul Reisert, Ryo Takahashi and Kentaro Inui. Distantly Supervised Biomedical Knowledge Acquisition via Knowledge Graph Based Attention.
  In Proceedings of First Workshop on Extracting Structured Knowledge from Scientific Publications (ESSP), June 2019. [paper]
• Qin Dai, Naoya Inoue, Paul Reisert and Kentaro Inui. Scientific Knowledge Acquisition via the Interaction between Relation Extraction and Knowledge Graph Completion.
  In Proceedings of Third International Workshop on SCIentific DOCument Analysis (SCIDOCA), November 2018. [Link]
• Qin Dai, Naoya Inoue, Paul Reisert and Kentaro Inui. Improving Scientific Relation Classification with Task Specific Supersense.
  In Proceedings of the 32nd Pacific Asia Conference on Language, Information and Computing (PACLIC32), December 2018.[paper]
• Qin Dai, Naoya Inoue, Paul Reisert, and Kentaro Inui. Leveraging Document-specific Information for Identifying Relations in Scientific Articles.
  In Proceedings of Second International Workshop on SCIentific DOCument Analysis (SCIDOCA), November 2017. [paper][Link]

Domestic Conference Papers

• Qin Dai, Benjamin Heinzerling and Kentaro Inui. Cross-stitching Text and Knowledge Graph Encoders for Distantly Supervised Relation Extraction.
  言語処理学会第29回年次大会, March 2023.
• Qin Dai, Benjamin Heinzerling and Kentaro Inui. Universal Graph based Relation Extraction.
  言語処理学会第28回年次大会, March 2022.
• Qin Dai, Naoya Inoue and Kentaro Inui. Improving Distantly Supervised Relation Extraction via Textual Representation of Multi-hop Inference over Text.
  言語処理学会第26回年次大会, March 2020.
• Qin Dai, Naoya Inoue, Paul Reisert and Kentaro Inui. End-to-End Scientific Knowledge Graph Completion via Word Embedding based Entity Type Classification.
  言語処理学会第25回年次大会, March 2019.

Reviewer

• ACL: 2023
• EMNLP: 2023, 2021
• COLING: 2024, 2022, 2020
• Journal of Natural Language Processing (JNLP): 2022

Awards

• Outstanding Paper Award at the 29th Annual Meeting of the Association of Natural Language Processing (NLP 2023)[Link]

Computer skills

• Languages: Python, C, JavaScript (basic)
• Machine Learning: PyTorch, TensorFlow, Keras, Theano

Hobbies

• Soccer, Jogging, Photography [Award]