HC-Search for Incremental Parsing

Liu, Yijia; Che, Wanxiang; Qin, Bing; Liu, Ting

HC-Search for Incremental Parsing

Yijia Liu, Wanxiang Che, Bing Qin, Ting Liu

Download BibTeX Cite

Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence. Pages 2887-2892.

Abstract

Standard incremental parsing algorithm employs a single scoring function and beam-search to find the best parse tree from an exponentially large search space. Inspired by recently proposed HC-search framework, we decompose the incremental parsing algorithm into two steps: first searching a set of high-quality outputs with beam-search, and second selecting the best output with a ranking model. We learn our incremental parsing model with a relaxed learning objective. We incorporate arbitrary features in our ranking model and learn the model from fine grain ranking examples. Experimental results on standard English and Chinese datasets show our method significantly outperforms a strong baseline.

Yijia Liu, Wanxiang Che, Bing Qin, and Ting Liu. 2016. HC-Search for Incremental Parsing. In Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-16. IJCAI, 2887–2892. https://ijcai.org/proceedings/2016/410

@inproceedings{ijcai2016p410,
  title     = {HC-Search for Incremental Parsing},
  author    = {Liu, Yijia and Che, Wanxiang and Qin, Bing and Liu, Ting},
  booktitle = {Proceedings of the Twenty-Fifth International Joint Conference on
               Artificial Intelligence, {IJCAI-16}},
  publisher = {AAAI Press / International Joint Conferences on Artificial Intelligence},
  editor    = {Subbarao Kambhampati},
  pages     = {2887--2892},
  year      = {2016},
  month     = {7},
  url       = {https://ijcai.org/proceedings/2016/410},
}

TY  - CPAPER
TI  - HC-Search for Incremental Parsing
AU  - Liu, Yijia
AU  - Che, Wanxiang
AU  - Qin, Bing
AU  - Liu, Ting
T2  - Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-16
PB  - AAAI Press / International Joint Conferences on Artificial Intelligence
PY  - 2016
SP  - 2887
EP  - 2892
UR  - https://ijcai.org/proceedings/2016/410
ER  -