I am a 4th-year undergraduate student in computer science at Yale University. I research natural language processing (NLP) and machine learning (ML), advised by Prof. Dragomir Radev (@ LILY lab) and Prof. John Lafferty.

My research aims to develop machine learning methods for natural language understanding. Recent interests include summarization (YZMPSR'17), semantic parsing (YYYZWLR'18), commonsense inference (annotated bib), and mathematical text modeling (YL'19). I am also interested in the robustness and interpretability of machine learning techniques (especially of neural networks) in NLP (YKR'18).

I co-organize a workshop on scientific document summarization at SIGIR 2018.


TopicEq: A Joint Topic and Mathematical Equation Model for Scientific Texts
Michihiro Yasunaga and John Lafferty
AAAI 2019.
[ paper | bibtex ]
ScisummNet: A Large Annotated Corpus and Content-Impact Models for Scientific Paper Summarization with Citation Networks
Michihiro Yasunaga, Jungo Kasai, Rui Zhang, Alexander Fabbri, Irene Li, Dan Friedman and Dragomir Radev
AAAI 2019.
[ paper | bibtex | project page ]
SyntaxSQLNet: Syntax Tree Networks for Complex and Cross-Domain Text-to-SQL Task
Tao Yu, Michihiro Yasunaga, Kai Yang, Rui Zhang, Dongxu Wang, Zifan Li and Dragomir Radev
EMNLP 2018.
[ paper | bibtex | project page | blog ]
Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task
Tao Yu, Rui Zhang, Kai Yang, Michihiro Yasunaga, Dongxu Wang, Zifan Li, James Ma, Irene Li, Qingning Yao, Shanelle Roman, Zilin Zhang and Dragomir Radev
EMNLP 2018.
[ paper | bibtex | project page | blog ]
Neural Coreference Resolution with Deep Biaffine Attention by Joint Mention Detection and Mention Clustering
Rui Zhang, Cicero Nogueira dos Santos, Michihiro Yasunaga, Bing Xiang and Dragomir Radev
ACL 2018.
[ paper | bibtex ]
Robust Multilingual Part-of-Speech Tagging via Adversarial Training
Michihiro Yasunaga, Jungo Kasai and Dragomir Radev
NAACL 2018.
[ paper | bibtex | slides ]
The CL-SciSumm Shared Task 2018: Results and Key Insights
Kokil Jaidka, Michihiro Yasunaga, Muthu Kumar Chandrasekaran, Dragomir Radev and Min-Yen Kan
BIRNDL 2018.
[ paper | bibtex | project page ]
Graph-based Neural Multi-Document Summarization
Michihiro Yasunaga, Rui Zhang, Kshitijh Meelu, Ayush Pareek, Krishnan Srinivasan and Dragomir Radev
Conference on Computational Natural Language Learning (CoNLL), 2017.
[ paper | bibtex ]

Other Projects

  • Named Entity Recognition for Academic Advising
    Developed systems to recognize and link academic named entities to university database. Part of the Sapphie Project with University of Michigan and IBM Research.
  • Medical NLP
    Develop NLP technologies to analyze electronic medical records (EMR).