DMCA
Monolingual machine translation for paraphrase generation (2004)
Cached
Download Links
| Venue: | In Proceedings of the 2004 Conference on Empirical Methods in Natural Language Processing |
| Citations: | 111 - 6 self |
BibTeX
@INPROCEEDINGS{Quirk04monolingualmachine,
author = {Chris Quirk and Chris Brockett and William Dolan},
title = {Monolingual machine translation for paraphrase generation},
booktitle = {In Proceedings of the 2004 Conference on Empirical Methods in Natural Language Processing},
year = {2004},
pages = {142--149}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
We apply statistical machine translation (SMT) tools to generate novel paraphrases of input sentences in the same language. The system is trained on large volumes of sentence pairs automatically extracted from clustered news articles available on the World Wide Web. Alignment Error Rate (AER) is measured to gauge the quality of the resulting corpus. A monotone phrasal decoder generates contextual replacements. Human evaluation shows that this system outperforms baseline paraphrase generation techniques and, in a departure from previous work, offers better coverage and scalability than the current best-of-breed paraphrasing approaches. 1
Keyphrases
monolingual machine translation paraphrase generation alignment error rate contextual replacement monotone phrasal decoder world wide web statistical machine translation human evaluation current best-of-breed paraphrasing approach novel paraphrase sentence pair previous work baseline paraphrase generation technique large volume input sentence news article
