DMCA
Recognizing Textual Entailment Using Probabilistic Inference
BibTeX
@MISC{Sha_recognizingtextual,
author = {Lei Sha and Sujian Li and Tingsong Jiang and Baobao Chang and Zhifang Sui},
title = {Recognizing Textual Entailment Using Probabilistic Inference},
year = {}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Recognizing Text Entailment (RTE) plays an important role in NLP applications in-cluding question answering, information retrieval, etc. In recent work, some re-search explore “deep ” expressions such as discourse commitments or strict logic for representing the text. However, these ex-pressions suffer from the limitation of in-ference inconvenience or translation loss. To overcome the limitations, in this paper, we propose to use the predicate-argument structures to represent the discourse com-mitments extracted from text. At the same time, with the help of the YAGO knowl-edge, we borrow the distant supervision technique to mine the implicit facts from the text. We also construct a probabilistic network for all the facts and conduct infer-ence to judge the confidence of each fact for RTE. The experimental results show that our proposed method achieves a com-petitive result compared to the previous work. 1
Keyphrases
textual entailment using probabilistic inference important role implicit fact predicate-argument structure nlp application in-cluding question answering yago knowl-edge com-petitive result distant supervision technique translation loss strict logic information retrieval re-search explore deep expression discourse com-mitments previous work probabilistic network discourse commitment recent work experimental result in-ference inconvenience text entailment
