How do people produce and understand languages robustly and efficiently; and
how can I build such a robust language processing mechanism for computers to interact with people via natural language?
I have been working on
(1) robust techniques for noisy text processing (e.g. word recognition, parsing, end-to-end models),
(2) question answering (QA), common sense knowledge acquisition, and
(3) NLP for educational purposes such as grammatical error correction, automated short answer scoring, quiz generation, and native language identification.
2018-04-27: I successfully defended my thesis.
2018-04-20: A paper was accepted to ACL on Efficient Annotation of Scalar Labels (EASL).
2018-03-30: I gave a talk at Allen Institute for Artificial Intelligence (AI2).
2018-02-22: I gave a video talk at Grammarly Research.
2018-02-09: I gave a talk at Amazon Research.
2017-12-14: I gave a talk at Chiba Institute of Technology (Japan).
2017-12-12: I gave a talk at NTT Communication Science Laboratories (Japan).
2017-12-08: I gave a talk at Tohoku University (Japan).
2017-12-05: I gave a talk at Tokyo Metropolitan University (Japan).
2017-10-18: I gave a presentation at Amazon Graduate Research Symposium.
2017-09-01: A paper was accepted to IJCNLP on Grammatical Error Correction with Neural Reinforcement Learning.
2017-07-01: A paper was accepted to BEA on Grammatical Error Correction into the Future.
2017-06-04: Our paper on error-repair dependency parsing received ACL 2017 Outstanding Paper Award.