融合词义消歧的汉语句法分析方法研究

doi:10.13209/j.0479-8023.2015.054

北京大学学报（自然科学版） ›› 2015, Vol. 51 ›› Issue (4): 577-584.DOI: 10.13209/j.0479-8023.2015.054

• 研究论文 • 下一篇

融合词义消歧的汉语句法分析方法研究

李冬晨;张献涛;樊扬;吴玺宏

北京大学言语听觉研究中心, 北京大学机器感知与智能教育部重点实验室, 北京 100871;

收稿日期:2014-04-02 修回日期:2014-05-20 出版日期:2015-07-20 发布日期:2015-07-20
吴玺宏
基金资助:
国家重点基础研究发展计划(2013CB329304)、公益健康行业研究专项(201202001)、国家社会科学基金(12&ZD119)和国家自然科学基金 (91120001)资助

Chinese Syntactic Parsing with Word Sense Disambiguation

LI Dongchen;ZHANG Xiantao;FAN Yang;WU Xihong

Speech and Hearing Research Center, Key Laboratory of Machine Perception (MOE), Peking University, Beijing 100871;

Received:2014-04-02 Revised:2014-05-20 Online:2015-07-20 Published:2015-07-20
About author:WU Xihong

摘要/Abstract

摘要： 将句法分析与词义消歧相结合, 根据层次化语义知识的句法分析框架, 在句法分析训练过程中, 利用句法结构信息对文法模型进行调整, 解决了引入语义时所面的歧义问题, 构建一种句法分析和词义消歧的一体化方法。实验表明, 在句法分析过程中进行词义消歧处理, 使句法分析的性能显著提升, 同时也获得词将句法分析与词义消歧相结合, 根据层次化语义知识的句法分析框架, 在句法分析训练过程中, 利用句法结构信息对文法模型进行调整, 解决了引入语义时所面对的歧义问题, 构建一种句法分析和词义消歧的一体化方法。实验表明, 在句法分析过程中进行词义消歧处理, 使句法分析的性能显著提升, 同时也获得词义消歧能将句法分析与词义消歧相结合, 根据层次化语义知识的句法分析框架, 在句法分析训练过程中, 利用句法结构信息对文法模型进行调整, 解决了引入语义时所面对的歧义问题, 构建一种句法分析和词义消歧的一体化方法。实验表明, 在句法分析过程中进行词义消歧处理, 使句法分析的性能显著提升, 同时也获得词义消歧能力。

关键词: 句法分析, 词义消歧, 一体化

Abstract: This paper proposes an integrated parsing and word sense disambiguation system. The ambiguity problem is solved when introducing semantic knowledge into the parser by modifying the lexical grammar iteratively. Syntactic information is used to deal with polysemous words in the training process. The experimental results show that the new method not only improves the parsing performance, but also has a good performance on word sense disambiguation.option and the closed fuel cycle (CFC) option which consists of the thermal reactor recycle (TRR) and the fast reactor along with thermal reactor recycle (FRR) are calculated. The natural uranium demand, the separate work demand, the nuclear power demand on alternative style of reactors, the nuclear assemblies demand and the disposal demand of nuclear wastes are obtained. According to these results, the FRR option is the optimal strategy with the highest utility of uranium as well as the minimum accumulation of the nuclear wastes.

Key words: parsing, word sense disambiguation, integration

中图分类号:

TP391

李冬晨;张献涛;樊扬;吴玺宏. 融合词义消歧的汉语句法分析方法研究[J]. 北京大学学报（自然科学版）, 2015, 51(4): 577-584.

LI Dongchen;ZHANG Xiantao;FAN Yang;WU Xihong. Chinese Syntactic Parsing with Word Sense Disambiguation[J]. , 2015, 51(4): 577-584.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: https://xbna.pku.edu.cn/CN/10.13209/j.0479-8023.2015.054

https://xbna.pku.edu.cn/CN/Y2015/V51/I4/577

参考文献

[1] Charniak E, Johnson M. Coarse-to-fine n-best parsing and maxent discriminative reranking // Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics. Michigan State, 2005: 173?180
[2] Collins M. Three generative, lexicalised models for statistical parsing // Proceedings of the Eighth 北京大学学报(自然科学版) 第51 卷第4 期 2015 年7 月 584 Conference on European Chapter of the Association for Computational Linguistics. Morristown, NJ, 1997: 16–23
[3] Collins M. Head-driven statistical models for natural language parsing [D]. Philadelphia: University of Pennsylvania, 1999
[4] Charniak E. A maximum-entropy-inspired parser // Proceedings of the 1st North American Chapter of the Association for Computational Linguistics Conference. Seattle, 2000: 132–139
[5] Petrov S, Barrett L, Thibaux R, et al. Learning accurate, compact, and interpretable tree annotation // Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual Meeting of the Association for Computational Linguistics. Sydney, 2006: 433–440
[6] Petrov S, Klein D. Improved inference for unlexicalized parsing // The Conference of the North American Chapter of the Association for Computational Linguistics. Rochester, 2007: 404–411
[7] Xiong D, Li S, Liu Q, et al. Parsing the Penn Chinese Treebank with semantic knowledge // Proc of the 2nd International Joint Conference on Natural Language Processing. Jeju Island, 2005: 70–81
[8] Agirre E, Baldwin T, Martinez D. Improving parsing and PP attachment performance with sense information // Proceedings of ACL-08: HLT. Columbus, OH, 2008: 317–325
[9] Bikel M, Chiang D. Two statistical parsing models applied to the Chinese Treebank // Proceedings of the Second Workshop on Chinese Language Processing: Held in Conjunction with the 38th Annual Meeting of the Association for Computational Linguistics — Volume 12. College Park, 2000: 1–6
[10] Lin X, Fan Y, Zhang M, et al. Refining grammars for parsing with hierarchical semantic knowledge // Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing. Morristown: Association for Computational Linguistics, 2009: 1298–1307
[11] Dong Z, Dong Q. Hownet a hybrid language and knowledge resource // Natural Language Processing and Knowledge Engineering. Beijing, 2003: 820–824
[12] Dong Z, Dong Q. HowNet and the computation of meaning. Singapore: World Scientific Publishing, 2006

融合词义消歧的汉语句法分析方法研究

Chinese Syntactic Parsing with Word Sense Disambiguation

PDF

PDF (翻译版)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 6

编辑推荐

Metrics

留言

[1]	王志芳, 周瑶瑾, 徐敏, 付宏鹏, 王思睿. 县域景观特征管理单元划分方法——以武胜县为例[J]. 北京大学学报自然科学版, 2020, 56(3): 553-560.
[2]	蒋炜, 李正华, 张民. 句法增强的UCCA语义分析方法[J]. 北京大学学报自然科学版, 2020, 56(1): 89-96.
[3]	杨安, 李素建, 李芸. 基于领域知识和词向量的词义消歧方法[J]. 北京大学学报自然科学版, 2017, 53(2): 204-210.
[4]	李宁,刘寅,梁琦,冯雪. 流式文档到固定版式文档的可逆转换方法研究[J]. 北京大学学报（自然科学版）, 2015, 51(2): 203-212.
[5]	陈强,何炎祥,刘续乐,孙松涛,彭敏,李飞. 基于句法分析的跨语言情感分析[J]. 北京大学学报（自然科学版）, 2014, 50(1): 55-60.
[6]	郑略省,吕学强,刘坤,林进. 汉语并列关系的识别研究[J]. 北京大学学报（自然科学版）, 2013, 49(1): 20-24.