Grammar as a Foreign LanguageEI
Syntactic constituency parsing is a fundamental problem in natural language processing and has been the subject of intensive research and engineering for decades. As a result, the most accurate parsers are domain specific, complex, and inefficient. In this paper we show that the domain agnostic attention-enhanced sequence-to-sequence model achieves state-of-the-art results on the most widely used syntactic constituency parsing dataset, when trained on a large synthetic corpus that was annotated using existing parsers. It also matches ...更多
- 1Milos Stanojevic, Minimalist Grammar Transition-Based Parsing.LACL, pp. 273-290, 2016.
- 2Yanyan Jia, Yansong Feng, Bingfeng Luo, Yuan Ye, Tianyang Liu, Dongyan Zhao. Transition-Based Discourse Parsing with Multilayer Stack Long Short Term Memory .NLPCC/ICCPOL, 2016.
- 5Ryan Georgi, Fei Xia, William D. Lewis. Capturing divergence in dependency trees to improve syntactic projection.CoRR, pp. 709-739, 2016.
- 8Xiangyu Duan, Jun Zhao, Bo Xu. Probabilistic Models for Action-Based Chinese Dependency Parsing.ECML, pp. 559-566, 2007.
- 11Gerold Schneider, James Dowdall, Fabio Rinaldi. A robust and hybrid deep-linguistic theory applied to large-scale parsing.ROMAND '04 Proceedings of the 3rd Workshop on RObust Methods in Analysis of Natural Language Data, pp. 14-23, 2004.
- 12Stephen Tratz, Eduard Hovy. A fast, accurate, non-projective, semantically-enriched parser.EMNLP, pp. 1257-1268, 2011.
- 14Roi Reichart, Ari Rappoport. Automatic Selection of High Quality Parses Created By a Fully Unsupervised Parser.CoNLL, pp. 156-164, 2009.
- 17Yi Zhang, Rui Wang. Correlating natural language parser performance with statistical measures of the text.KI, pp. 217-224, 2009.
- 19Kenji Sagae, Self-training without reranking for parser domain adaptation and its impact on semantic role labeling.DANLP 2010 Proceedings of the 2010 Workshop on Domain Adaptation for Natural Language Processing, pp. 37-44, 2010.
- 20Slav Petrov, Pi-Chuan Chang, Michael Ringgaard, Hiyan Alshawi. Uptraining for accurate deterministic question parsing.EMNLP, pp. 705-713, 2010.
neural information processing systems, Volume abs/1412.74492014,