DFKI-LT - Using Discourse Information for Paraphrase Extraction

Michaela Regneri, Rui Wang
Using Discourse Information for Paraphrase Extraction
1 Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, Pages 916-927, Jeju Island, Korea, Republic of, Association for Computational Linguistics, 7/2012
 
Previous work on paraphrase extraction using parallel or comparable corpora has generally not considered the documents’ discourse structure as a useful information source. We propose a novel method for collecting paraphrases relying on the sequential event order in the discourse, using multiple sequence alignment with a semantic similarity measure. We show that adding discourse information boosts the performance of sentence-level paraphrase acquisition, which consequently gives a tremendous advantage for extracting phrase-level paraphrase fragments from matched sentences. Our system beats an informed baseline by a margin of 50%.
 
Files: BibTeX, D12-1084, D12-1084.pdf