蘊涵句型分析於改進中文文字蘊涵識別系統

Entailment Analysis for Improving Chinese Recognizing Textual Entailment System

楊善順(Shan-Shun Yang) ； 吳世弘(Shih-Hung Wu) ； 陳良圃(Liang-Pu Chen) ； 邱宏昇(Hung-Sheng Chiu) ； 楊仁達(Ren-Dar Yang)

《中文計算語言學期刊》 18卷4期 (2013/12) Pp. 1-16

摘要

文字蘊涵是自然語言處理最近興起的研究課題。文字蘊涵識別（Recognizing Textual Entailment, RTE）可以應用到其他許多自然語言處理的研究中。在本文中將介紹我們在觀察NTCIR-10-RITE-2資料集後發現過去系統的缺陷，進而提出如何改進中文文字蘊涵系統的方法。過去的系統處理文字蘊涵多使用機器學習分類文題的方法，所有輸入句子都用同樣的分類器處理，對於某些特別的問題往往會產生誤判。我們認為應該針對於特定類型的問題做處理，增加系統可以處理的問題類型。實驗結果顯示配合之前提出的機器學習方法，增加四種特殊類型分類對特殊類型句子進行個別處理，可以有效改進系統，實驗結果系統在識別簡體中文蘊涵兩類的正確率從原本67.86%提昇到72.92%。

關鍵字

中文文字蘊涵識別 ； 蘊涵分析

並列摘要

Recognizing Textual Entailment (RTE) is a new research issue in natural language processing (NLP) research area. RTE can be a useful component in many NLP applications. In this paper, we introduce our finding on the entailment analysis of the NTCIR-10 RITE-2 dataset, and use the observation to improve our system. In the previous works, all the input pairs are treated equally in a standard classification architecture. We find that is not suitable for some special cases. We believe that by isolating the special cases and building separated classifiers, a RTE system can perform better. After implementing modules for four special cases into our system, the result is significantly improved from 67.86% to 72.92% on the binary class classification task.

並列關鍵字

Chinese Recognizing Textual Entailment ； Entailment Analysis

參考文獻

Li, M. H.,Wu, S. H.,Zeng, Y. C.,Yang, P. C.,Ku, T.(2010).Chinese Characters Conversion System based on Lookup Table and Language Model.International Journal of Computational Linguistics and Chinese Language Processing.15(1),19-36.

Liu, Q.,Li, S. J.(2002).Word Similarity Computing Based on How-net.International Journal of Computational Linguistics and Chinese Language Processing.7(2),59-76.

Dagan, I.,Glickman, O.(2004).Probabilistic textual entailment: Generic applied modeling of language variability.Proceedings of the Workshop on Learning Methods for Text Understanding and Mining.(Proceedings of the Workshop on Learning Methods for Text Understanding and Mining).:

Dagan, I.,Glickman, O.,Magnini, B.(2006).The PASCAL recognizing textual entailment challenge.

Hua, D. B.,Dinga, J.(2011).Study on Similar Engineering Decision Problem Identification Based on Combination of Improved Edit-Distance and Skeletal Dependency Tree with POS.Systems Engineering Procedia.1,406-413.