该文对基于语义解析的中文地理信息系统(GIS)自然语言接口实现技术与方法进行了探索性的研究。首先,我们针对一个具体GIS应用领域设计和开发了一种函数式的形式化意义表示语言GISQL和一个中文语义解析标注语料库;然后,我们通过引入混合树作为隐变量用于构造输入句子与输出表示结构之间的对应关系,提出了一种基于含隐变量的感知器模型的语义解析算法。在开发的中文语义解析标注语料库上的实验结果显示,该文提出的语义解析算法的F1值达到了90.67％,明显优于baseline系统。更重要的是,该文的研究证明了基于语义解析方法实现中文GIS的自然语言接口是一种有效可行的途径。
Abstract
Natural Language Interfaces (NLIs) to the Geographical Information Systems (GISs) have not received a lot of attention in computational linguistics, in spite of the potential values of such systems for users of GISs. This paper presents a pilot study of implementing Chinese NLIs to GISs based on semantic parsing. First, we design a formal meaning representation language (MRL) related to a specific GIS application and develop a corresponding corpus. Second, we translate the natural language questions into GIS queries in MRL using semantic parsing. In particular, we propose a semantic parsing approach based on a latent structural perceptron with hybrid tree. Our evaluation results on the developed corpus show that the proposed methods significantly outperform the baseline approaches, and more importantly, demonstrate that it is feasible to build such NLIs to GISs using semantic parsing.
关键词
地理信息系统 /
自然语言接口 /
语义解析
{{custom_keyword}} /
Key words
geographical information systems /
natural language interfaces /
semantic parsing.
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 张连蓬,储美华,刘国林,江涛. 车载智能地理信息查询系统及其自然语言接口[J]. 现代测绘, 2005, 28(1): 20-23.
[2] 马林兵, 龚健雅. 空间信息自然语言查询接口的研究与应用[J]. 武汉大学学报(信息科学版), 2003, 28 (3): 301-305.
[3] S Mador-Haim, Y Winter, A Braun. Controlled language for geographical information system queries[C]//Proceedings of Inference in Computational Semantics, 2006.
[4] 余明朗, 明小娜, 龙毅, 张雪英. GIS环境下中文命令的规则匹配与语义解析[J]. 地理与地理信息科学, 2012, 28(6): 7-12.
[5] R J Kate, Y W Wong, R J Mooney. Learning to transform natural to formal languages[C]//Proceedings of AAAI, 2005: 1062-1068.
[6] Y W Wong, R J Mooney. Learning for semantic parsing with statistical machine translation[C]//Proceedings of the HLT-NAACL, 2006: 439-446.
[7] Wei Lu, Hwee Tou Ng, Wee Sun Lee, Luke S. Zettlemoyer. A Generative Model for Parsing Natural Language to Meaning Representations[C]//Procee-dings of EMNLP, 2008: 913-920.
[8] Tom Kwiatkowski, Luke Zettlemoyer, Sharon Goldwater, Mark Steedman. Inducing probabilistic CCG grammars from logical form with higher-order unification[C]//Proceeding of EMNLP, 2010: 1223-1233.
[9] John M. Zelle, Raymond J. Mooney. Learning to parse database queries using inductive logic programming[C]//Proceedings of AAAI, 1996: 1050-1055.
[10] C N J Yu, T Joachims. Learning structural svms with latent variables[C]//Proceedings of ICML, 2009.
[11] Junsheng Zhou, Juhong Xu, Weiguang Qu. Efficient Latent Structural Perceptron with Hybrid Trees for Semantic Parsin[C]//Proceedings of the IJCAI, 2013: 2246-2252.
[12] Michael Collins. Discriminative training methods for hidden Markov models: Theory and experiments with perceptron algorithms[C]//Proceeding of EMNLP, 2002.
[13] Xu Sun, Takuya Matsuzaki, Daisuke Okanohara Junichi Tsujii. Latent Variable Perceptron Algorithm for Structured Classification[C]//Proceedings of IJCAI, 2009: 1236-1242.
[14] Ryan McDonald. Discriminative Training and Spanning Tree Algorithms for Dependency Parsing[D]. University of Pennsylvania, PhD Thesis, 2006.
[15] D L Lee, H Chuang, K Seamons. Document Ranking and the Vector-Space Model[J]. IEEE Software, 1997, 14(2): 67-75.
[16] Yuk Wah Wong, Raymond J. Mooney. Learning Synchronous Grammars for Semantic Parsing with Lambda Calculus[C]//Proceedings of ACL, 2007: 203-210.
[17] Peng Li, Yang Liu, Maosong Sun. An Extended GHKM Algorithm for Inducing -SCFG[C]//Proceedings of AAAI, 2013: 605-611.
[18] L S Zettlemoyer, M Collins. Online learning of relaxed CCG grammars for parsing to logical form[C]//Proceedings of EMNLP-CoNLL, 2007: 678-687.
[19] Mark Steedman. The Syntactic Process[M]. The MIT Press, Cambridge, Mass,2000.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
国家自然科学基金(61073119, 61272221,61472191);江苏省社科基金(12YYA002);数字制图与国土信息应用工程国家测绘地理信息局重点实验室开放研究基金(Gcwd201411).
{{custom_fund}}
PDF(1614 KB)
