Extracting Lexically Divergent Paraphrases from Twitter

Wei Xu, Alan Ritter, Chris Callison-Burch, William B. Dolan, Yangfeng Ji


Abstract
We present MultiP (Multi-instance Learning Paraphrase Model), a new model suited to identify paraphrases within the short messages on Twitter. We jointly model paraphrase relations between word and sentence pairs and assume only sentence-level annotations during learning. Using this principled latent variable model alone, we achieve the performance competitive with a state-of-the-art method which combines a latent space model with a feature-based supervised classifier. Our model also captures lexically divergent paraphrases that differ from yet complement previous methods; combining our model with previous work significantly outperforms the state-of-the-art. In addition, we present a novel annotation methodology that has allowed us to crowdsource a paraphrase corpus from Twitter. We make this new dataset available to the research community.
Anthology ID:
Q14-1034
Volume:
Transactions of the Association for Computational Linguistics, Volume 2
Month:
Year:
2014
Address:
Cambridge, MA
Editors:
Dekang Lin, Michael Collins, Lillian Lee
Venue:
TACL
SIG:
Publisher:
MIT Press
Note:
Pages:
435–448
Language:
URL:
https://aclanthology.org/Q14-1034
DOI:
10.1162/tacl_a_00194
Bibkey:
Cite (ACL):
Wei Xu, Alan Ritter, Chris Callison-Burch, William B. Dolan, and Yangfeng Ji. 2014. Extracting Lexically Divergent Paraphrases from Twitter. Transactions of the Association for Computational Linguistics, 2:435–448.
Cite (Informal):
Extracting Lexically Divergent Paraphrases from Twitter (Xu et al., TACL 2014)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-3/Q14-1034.pdf
Code
 cocoxu/twitterparaphrase