Bidirectional Transition-Based Dependency Parsing

Saved in:
Bibliographic Details
Title: Bidirectional Transition-Based Dependency Parsing
Authors: Yong Jiang, Kewei Tu, Yunzhe Yuan
Source: Proceedings of the AAAI Conference on Artificial Intelligence. 33:7434-7441
Publisher Information: Association for the Advancement of Artificial Intelligence (AAAI), 2019.
Publication Year: 2019
Subject Terms: 0211 other engineering and technologies, 0202 electrical engineering, electronic engineering, information engineering, 02 engineering and technology
Description: Transition-based dependency parsing is a fast and effective approach for dependency parsing. Traditionally, a transitionbased dependency parser processes an input sentence and predicts a sequence of parsing actions in a left-to-right manner. During this process, an early prediction error may negatively impact the prediction of subsequent actions. In this paper, we propose a simple framework for bidirectional transitionbased parsing. During training, we learn a left-to-right parser and a right-to-left parser separately. To parse a sentence, we perform joint decoding with the two parsers. We propose three joint decoding algorithms that are based on joint scoring, dual decomposition, and dynamic oracle respectively. Empirical results show that our methods lead to competitive parsing accuracy and our method based on dynamic oracle consistently achieves the best performance.
Document Type: Article
ISSN: 2374-3468
2159-5399
DOI: 10.1609/aaai.v33i01.33017434
Access URL: https://ojs.aaai.org/index.php/AAAI/article/download/4733/4611
https://ojs.aaai.org/index.php/AAAI/article/view/4733
http://kms.shanghaitech.edu.cn/handle/2MSLDSTB/29219
https://ojs.aaai.org/index.php/AAAI/article/download/4733/4611
https://aaai.org/ojs/index.php/AAAI/article/view/4733
https://wvvw.aaai.org/ojs/index.php/AAAI/article/download/4733/4611
https://dblp.uni-trier.de/db/conf/aaai/aaai2019.html#YuanJT19
Rights: URL: https://www.aaai.org
Accession Number: edsair.doi.dedup.....5de8ea5f01f45bf6be921bf4e9e37c7c
Database: OpenAIRE
Description
Abstract:Transition-based dependency parsing is a fast and effective approach for dependency parsing. Traditionally, a transitionbased dependency parser processes an input sentence and predicts a sequence of parsing actions in a left-to-right manner. During this process, an early prediction error may negatively impact the prediction of subsequent actions. In this paper, we propose a simple framework for bidirectional transitionbased parsing. During training, we learn a left-to-right parser and a right-to-left parser separately. To parse a sentence, we perform joint decoding with the two parsers. We propose three joint decoding algorithms that are based on joint scoring, dual decomposition, and dynamic oracle respectively. Empirical results show that our methods lead to competitive parsing accuracy and our method based on dynamic oracle consistently achieves the best performance.
ISSN:23743468
21595399
DOI:10.1609/aaai.v33i01.33017434