Abstract：Despite of the rapid development of natural language processing,studies at the syntax level can’t fully satisfy what we need. Semantics is becoming a hot research topic in the NLP community. As the key part of semantics,computational semantic compositionality receives more attention. In this paper,we classify the approaches towards computational semantic compositionality into two categories: linguistic methods and distributional methods. We present some typical studies for each category,including the recent deep learning approaches. After an introduction to these two approaches,we make a comparison between linguistic methods and distributional methods. Then we introduce several applications of computational semantic compositionality on sentiment analysis and machine translation. Finally,we provide some suggestions on future directions of computational semantic compositionality.
[1] 冯志伟. 自然语言处理的历史与现状[J]. 中国外语，2008，01:14-22. [2]Kartsaklis D. Compositional Operators in Distributed Semantics. Springer Science Reviews[OL]. DOI: 10.1007/s40362-014-0017-z. 2014. www.cs.ox.ac.uk/files/6248/kartsaklis-springer.pdf [3]Cornford FM,ed. Plato's theory of knowledge: The theaetetus and the sophist[M]. Courier Dover Publications,2003. [4]Frege G. ‘Uber Sinn und Bedeutung’,in P Geach and M Black,eds.Translations from the Philosophical Writings of Gottlob[M]. Oxford: Blackwell,1892: 56-78. [5]Partee B. Lexical semantics and compositionality[J]. An invitation to cognitive science: Language. 1995. 1: 311-360. [6]Clark S,Pulman S. Combining Symbolic and Distributional Models of Meaning[C]//Proceedings of the AAAI Spring Symposium on Quantum Interaction,2007: 52-55. [7]Blacoe W,Lapata M. A comparison of vector-based representations for semantic composition[C]//Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning. Association for Computational Linguistics,2012: 546-556. [8]Montague R. English as a formal language[J]. Linguaggi nella societae nella tecnica. 1970: 189-224. [9]Moggi E. Computational lambda-calculus and monads[M]. University of Edinburgh,Department of Computer Science,Laboratory for Foundations of Computer Science,1988.[ZK)] [10]Guevara E. Computing semantic compositionality in distributional semantics[C]//Proceedings of the 9th International Conference on Computational Semantics.Association for Computational Linguistics,2011: 135-144. [11]Bach E. An extension of classical transformational grammar[C]//Proceedings of the 1976 Conference at Michigan State University,1976: 183-224. [12]Church A. The calculi of lambda-conversion[M]. Princeton University Press,1985. [13]石静,吴云芳,邱立坤等. 基于大规模语料库的汉语词义相似度计算方法[J]. 中文信息学报，2013，27(1)1-6，80. [14]王鑫,孙薇薇,穗志方.基于浅层句法分析的中文语义角色标注研究[J]. 中文信息学报，2011，(25)01: 116-122. [15]Mitchell J,Lapata M. Vector-based Models of Semantic Composition[C]//Proceedings of the 46th Annual Meeting of the Association for Computational Linguistics,2008: 236-244. [16]Harris Z S. Mathematical structures of language[J]. Wiley. New York. 1968. [17]Coecke B,Sadrzadeh M,Clark S.Mathematical Foundations for Distributed Compositional Model of Meaning[J]. Lambek Festschrift. Linguistic Analysis. 2010，36: 345-384. [18]Baroni M,Zamparelli R. Nouns are vectors,adjectives are matrices: Representing adjective-noun constructions in semantic space[C]//Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics,2010: 1183-1193. [19]Hinton G E,Salakhutdinov R R. Reducing the dimensionality of data with neural networks[J]. Science,2006，313(5786): 504-507. [20]Socher R,Lin C C,Manning C,et al. Parsing natural scenes and natural language with recursive neural networks[C]//Proceedings of the 28th International Conference on Machine Learning (ICML-11),2011，129-136. [21]Socher R,Huval B,Manning C D,et al. Semantic compositionality through recursive matrix-vector spaces[C]//Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning. Association for Computational Linguistics,2012，1201-1211. [22]Collobert R,Weston J,Bottou L,et al. Natural language processing (almost) from scratch[J]. The Journal of Machine Learning Research,2011，12: 2493-2537. [23]Mitchell J,Lapata M. Composition in distributional models of semantics[J]. Cognitive science,2010，34(8): 1388-1429. [24]Pang B,Lee L,Vaithyanathan S. Thumbs up?: sentiment classification using machine learning techniques[C]//Proceedings of the ACL-02 Conference on Empirical Methods in Natural Language Processing-Volume 10. Association for Computational Linguistics,2002: 79-86. [25]Socher R,Pennington J,Huang E H,et al. Semi-supervised recursive autoencoders for predicting sentiment distributions[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics,2011: 151-161. [26]刘群. 统计机器翻译综述[J]. 中文信息学报,2003，17(4): 1-12. [27]Gao J,He X,Yih W,et al. Learning Continuous Phrase Representations for Translation Modeling[C]//Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics: Long Papers-Volume 1. Association for Computational Linguistics. Baltimore,Maryland. 2014: 699-709. [28]He X,Deng L. Maximum expected bleu training of phrase and lexicon translation model[C]//Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics,2012: 292-301. [29]Hermann K M,Blunsom P. Multilingual Models for Compositional Distributed Semantics[C]//Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics,2014: 58-68.
2016, Vol. 30 
