Title :
Word alignment based recognizing textural entailment
Author :
Zhang, Xinhua ; Wang, Yinglin ; Li, Peng
Author_Institution :
Dept. of Comput. Sci. & Eng., Shanghai Jiao-Tong Univ., Shanghai, China
Abstract :
In this paper we focus on finding a best semantic alignment between two sentences. We model it as a bipartite weighted matching, and it can be solved in polynomial time by using combinational optimization method. Base on this alignment we integrated several methods to perform recognizing textural entailment (RTE). Finally, we implement our method on to RTE1 Test Data. The result shows that word alignment based RTE has a good performance.
Keywords :
combinatorial mathematics; optimisation; pattern recognition; word processing; bipartite weighted matching; combinational optimization method; textural entailment recognition; word alignment; Accuracy; Electronic publishing; Information services; Internet; RTE; structure prediction; word alignment;
Conference_Titel :
Progress in Informatics and Computing (PIC), 2010 IEEE International Conference on
Conference_Location :
Shanghai
Print_ISBN :
978-1-4244-6788-4
DOI :
10.1109/PIC.2010.5687955
