Abstract
Different from the current syntax parsing based on deep learning, we present a novel Chinese parsing method, which is based on Sliding Match of Semantic String (SMOSS). (1) Training stage: In a treebank, headwords of tree nodes are represented by semantic codes given in the Synonym Dictionary (Tongyici Cilin). N-gram semantic templates are extracted from every layer of a syntax tree by means of sliding window to establish one N-gram semantic template library. (2) Parsing stage: Words of a sentence, including headwords of chunks, are represented by the semantic codes from Tongyici Cilin. With the sliding window method, N-gram semantic code strings are extracted to match with the templates in the N-gram semantic template library; subsequently, the mapping information of the matched templates is employed to guide the chunking of semantic code strings. The Chinese syntax parsing is completed through continuous matching and chunking. On the same training scale, N-gram semantic template can create favorable conditions for flexible matching and improve the syntax parsing performance. With train and test sets from the Tsinghua Chinese Treebank (TCT), the results are F1-score 99.71% (closed test) and F1-score 70.43% (open test), respectively.
- Steven Abney. 1996. Partial parsing via finite state cascades. Nat. Lang. Eng. 2, 4 (1996), 337--344. Google Scholar
Digital Library
- Chris Alberti, Daniel Andor, Ivan Bogatyy, Michael Collins, Dan Gillick, Lingpeng Kong, Terry Koo, Ji Ma, Mark Omernick, Slav Petrov, Chayut Thanapirom, Zora Tung, and David Weiss. 2017. SyntaxNet models for the CoNLL2017 shared task. arXiv:1703.04929, 1--6.Google Scholar
- Chris Alberti, David Weiss, Greg Coppola, and Slav Petrov. 2015. Improved transition-based parsing and tagging with neural networks. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP’15). 1354--1359.Google Scholar
Cross Ref
- Miguel Ballesteros, Chris Dyer, and Noah A. Smith. 2015. Improved transition-based parsing by modeling characters instead of words with LSTMs. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP’15). 1--11.Google Scholar
- Jacob Buckman, Miguel Ballesteros, and Chris Dyer. 2016. Transition-based dependency parsing with heuristic backtracking. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing. 2313--2318.Google Scholar
Cross Ref
- Danqi Chen and Christopher D. Manning. 2014. A fast and accurate dependency parser using neural networks. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP’14). 1--11.Google Scholar
- Wenliang Chen, Muhua Zhu, Min Zhang, Yue Zhang, and Jingbo Zhu. 2017. Improving shift-reduce phrase-structure parsing with constituent boundary information. Comput. Intell. 33, 3 (2017), 428--447.Google Scholar
Cross Ref
- Hao Cheng, Hao Fang, He xiao dong, Gao jian feng, and Li Deng. 2016. Bi-directional attention with agreement for dependency parsing. arXiv:1608.02076v2 {cs.CL} (2016), 1--11.Google Scholar
- Timothy Dozat and Christopher D. Manning. 2017. Deep biaffine attention for neural dependency paring. In Proceedings of the International Conference on Learning Representations (ICLR’17). 1--8.Google Scholar
- Greg Durrett and Dan Klein. 2015. Neural CRF parsing. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and 7th International Joint Conference on Natural Language Processing. 302--312.Google Scholar
Cross Ref
- Chris Dyer, Adhiguna Kuncoro, Miguel Ballesteros, and Noah A. Smith. 2016. Recurrent neural network grammars. arXiv:1602.07776v4 (2016), 1--13.Google Scholar
- Chris Dyer, Miguel Ballesteros, Wang Ling, Austin Matthews, and Noah A. Smith. 2015. Transition-based dependency parsing with stack long short-term memory. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics. 334–343.Google Scholar
- Vanessa Wei Feng and Graeme Hirst. 2014. A linear-time bottom-up discourse parser with constraints and post-editing. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics. 511--521.Google Scholar
Cross Ref
- Daniel Fernández-González and Carlos Gómez-Rodríguez. 2018. Faster shift-reduce constituent parsing with a non-binary, bottom-up strategy. arXiv:1804.07961v1 (2018), 1--10.Google Scholar
- Xianghao Geng, Junhui Li, Guodong Zhou, and Qiaoming Zhu. 2009. A history-based hierarchical chinese parsing. Comput. Appl. Softw. 26, 6 (2009), 45--47, 51.Google Scholar
- Cross James and Liang Huang. 2016. Incremental parsing with minimal features using bi-directional LSTM. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics. 32--37.Google Scholar
- Zhipeng Jiang, Yi Guan, and Xishuang Dong. 2014. A Chinese hierarchical parsing approach based on multi-layer collaborative correction. J. Chin. Inf. Process. 28, 4 (2014), 29--36.Google Scholar
- Zhipeng Jiang, Yu Zhao, Yi Guan, Chao Li, and Sheng Li. 2010. Complete syntactic analysis bases on multi-level chunking. In Proceedings of the Joint Conference on Chinese Language Processing (CIPS-SIGHAN’10). 1--5.Google Scholar
- Eliyahu Kiperwasser and Yoav Goldberg. 2016a. Easy-first dependency parsing with hierarchical tree LSTMs. Trans. Assoc. Comput. Ling. 4 (2016), 445--461.Google Scholar
Cross Ref
- Eliyahu Kiperwasser and Yoav Goldberg. 2016b. Simple and accurate dependency parsing using bidirectional LSTM feature representations. arXiv:1603.04351v3 {cs.CL} (2016), 1--15.Google Scholar
- Shuhei Kurita, Daisuke Kawahara, and Sadao Kurohashi. 2017. Neural joint model for transition-based chinese syntactic analysis. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics. 1204--1214.Google Scholar
Cross Ref
- Haonan Li, Zhisong Zhang, Yuqi Ju, and Hai Zhao. 2018. Neural character-level dependency parsing for Chinese. In Proceedings of the 32nd AAAI Conference on Artificial Intelligence (AAAI-18). 5205--5212.Google Scholar
- Jingyi Li, Lingling Mu, Hongying Zan, and Kunli Zhang. 2015. Research on Chinese parsing based on the improved compositional vector grammar. In Proceedings of the Chinese Lexical Semantics Workshop (CLSW’15), Lecture Notes in Artificial Intelligence, Vol. 9332, 649--658.Google Scholar
Cross Ref
- Zuchao Li, Jiaxun Cai, Shexia He, and Hai Zhao. 2018. Seq2seq dependency parsing. In Proceedings of the 27th International Conference on Computational Linguistics. 3203--3214.Google Scholar
- Hang Liu, Mingtong Liu, Yujie Zhang, Jinan Xu, and Yufeng Chen. 2018. improved character-based chinese dependency parsing by using stack-tree LSTM. In Proceedings of the CCF International Conference on Natural Language Processing and Chinese Computing (NLPCC’18), Lecture Notes in Artificial Intelligence, Vol. 11109, 203--212.Google Scholar
Cross Ref
- Jiangming Liu and Yue Zhang. 2017a. Shift-reduce constituent parsing with neural lookahead features. Trans. Assoc. Comput. Ling. 5 (2017), 45--58.Google Scholar
Cross Ref
- Jiangming Liu and Yue Zhang. 2017b. In-order transition-based constituent parsing. Trans. Assoc. Comput. Ling. 5 (2017), 413--424.Google Scholar
Cross Ref
- Yang Liu and Mirella Lapata. 2017. Learning contextually informed representations for linear-time discourse parsing. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing. 1300--1309.Google Scholar
Cross Ref
- Haitao Mi and Liang Huang. 2015. Shift-reduce constituency parsing with dynamic programming and POS tag lattice. In Proceedings of the 2015 Annual Conference of the North American Chapter of the ACL. 1030--1035.Google Scholar
Cross Ref
- Slav Petrov and Dan Klein. 2007. Improved inference for unlexicalized parsing. In Proceedings of the Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (HLT-NAACL’07). 1--8.Google Scholar
- Yikang Shen, Zhouhan Lin, Athul Paul Jacob, Alessandro Sordoni, Aaron Courville, and Yoshua Bengio. 2018. Straight to the tree: Constituency parsing with neural syntactic distance. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics. 1171--1180.Google Scholar
Cross Ref
- Weiwei Sun, Yufei Chen, Xiaojun Wan, and Meichun Liu. 2018. Parsing Chinese sentences with grammatical relations. Comput. Ling. 45, 1 (2018), 95--136. Google Scholar
Digital Library
- Zhiyang Teng and Yue Zhang. 2018. Two local models for neural constituent parsing. In Proceedings of the 27th International Conference on Computational Linguistics. 119--132.Google Scholar
- Yoshimasa Tsuruoka. 2009. Fast full parsing by linear-chain conditional random fields. In Proceedings of the 12th Conference of the European Chapter of the ACL. 790--798. Google Scholar
Digital Library
- Wei Wang and Degen Huang. 2014. A syntactic parsing method based on sliding matching of semantic string. China patent: CN 103500160 A. 2014.Google Scholar
- Wenhui Wang and Baobao Chang. 2016. Graph-based dependency parsing with bidirectional LSTM. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics. 2306--2315.Google Scholar
Cross Ref
- Zhiguo Wang and Nianwen Xue. 2014. Joint POS tagging and transition-based constituent parsing in Chinese with non-local features. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics. 733--742.Google Scholar
Cross Ref
- Zhiguo Wang, Haitao Mi, and Nianwen Xue. 2015. Feature optimization for constituent parsing via neural networks. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics. 1138--1147.Google Scholar
Cross Ref
- Taro Watanabe and Eiichiro Sumita. 2015. Transition-based neural constituent parsing. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing. 1169--1179.Google Scholar
Cross Ref
- Fuxiang Wu. 2017. Dependency parsing with transformed feature. Information 8, 13 (2017), 1--11.Google Scholar
Cross Ref
- Meishan Zhang, Yue Zhang, Wanxiang Che, Ting Liu. 2014. Character-level chinese dependency parsing. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics. 1326--1336.Google Scholar
Cross Ref
- Xingxing Zhang, Jianpeng Cheng, and Mirella Lapata. 2016. Dependency parsing as head selection. arXiv:1606.01280v4 {cs.CL} (2016), 1--12.Google Scholar
- Yuan Zhang, Chengtao Li, Regina Barzilay, and Kareem Darwish. 2015. Randomized greedy inference for joint segmentation, POS tagging and dependency parsing. In Proceedings of the 2015 Annual Conference of the North American Chapter of the ACL: Human Language Technologies. 42--52.Google Scholar
Cross Ref
- Zhirui Zhang, Shujie Liu, Mu Li, Ming Zhou, and Enhong Chen. 2017. Stack-based multi-layer attention for transition-based dependency parsing. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing. 1678--1683.Google Scholar
Cross Ref
- Zhisong Zhang, Hai Zhao, and Lianhui Qin. 2016. Probabilistic Graph-based Dependency Parsing with Convolutional Neural Network. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics. 1382--1392.Google Scholar
Cross Ref
- Qiuye Zhao and Qun Liu. 2016. A subtree-based factorization of dependency parsing. In Proceedings of the 26th International Conference on Computational Linguistics: Technical Papers (COLING’16). 589--598.Google Scholar
- Lvexing Zheng, Houfeng Wang, and Xueqiang Lv. 2015. Improving Chinese dependency parsing with lexical semantic features. In Proceedings of the CCF International Conference on Natural Language Processing and Chinese Computing (NLPCC’15), Lecture Notes in Artificial Intelligence, Vol. 9362, 36--46. Google Scholar
Digital Library
- Xiaoqing Zheng. 2017. Incremental graph-based neural dependency parsing. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing. 1655--1665.Google Scholar
Cross Ref
- Hao Zhou, Shujian Huang, Junsheng Zhou, Yue Zhang, Huadong Chen, Xingyu Dai, Chuan Cheng, and Jiajun Chen. 2016. Shift-reduce constituent parsing with action N-gram model. ACM Trans. Asian Low-Resource Lang. Inf. Process. 15, 3 (2016), 1--17. Google Scholar
Digital Library
- Qiaoli Zhou, Wenjing Lang, Yingyin Wang, Yan Wang, and Dongfeng Cai. 2010. The SAU Report for the first CIPS-SIGHAN-ParsEval-2010. In Proceedings of the Joint Conference on Chinese Language Processing (CIPS-SIGHAN’10). 1--8.Google Scholar
Index Terms
Chinese Syntax Parsing Based on Sliding Match of Semantic String
Recommendations
Neural Character-Level Syntactic Parsing for Chinese
In this work, we explore character-level neural syntactic parsing for Chinese with two typical syntactic formalisms: the constituent formalism and a dependency formalism based on a newly released character-level dependency treebank. Prior works in Chinese ...
Syntax Parsing: Implementation Using Grammar-Rules for English Language
ICESC '14: Proceedings of the 2014 International Conference on Electronic Systems, Signal Processing and Computing TechnologiesSyntactic parsing deals with syntactic structure of a sentence. The word 'syntax' refers to the grammatical arrangement of words in a sentence and their relationship with each other. The objective of syntactic analysis is to find syntactic structure of ...
Improve Chinese Semantic Dependency Parsing via Syntactic Dependency Parsing
IALP '12: Proceedings of the 2012 International Conference on Asian Language ProcessingWe address the problem of Chinese semantic dependency parsing. Dependency parsing is traditionally oriented to syntax analysis, which we denote by syntactic dependency parsing to distinguish it from semantic dependency parsing. In this paper, firstly we ...






Comments