Abstract / Description of output
We consider the problem of learning general-purpose, paraphrastic sentence embeddings in the setting of Wieting et al. (2016b). We use neural machine translation to generate sentential paraphrases via back- translation of bilingual sentence pairs. We evaluate the paraphrase pairs by their ability to serve as training data for learning paraphrastic sentence embeddings. We find that the data quality is stronger than prior work based on bitext and on par with manually-written English paraphrase pairs, with the advantage that our approach can scale up to generate large training sets for many languages and domains. We experiment with several language pairs and data sources, and develop a variety of data filtering techniques. In the process, we explore how neural machine translation output differs from human-written sentences, finding clear differences in length, the amount of repetition, and the use of rare words.1
1: Generated paraphrases and code are available at http://ttic.uchicago.edu/˜wieting.
1: Generated paraphrases and code are available at http://ttic.uchicago.edu/˜wieting.
Original language | English |
---|---|
Title of host publication | Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing |
Publisher | Association for Computational Linguistics |
Pages | 274-285 |
Number of pages | 12 |
DOIs | |
Publication status | Published - 11 Sept 2017 |
Event | EMNLP 2017: Conference on Empirical Methods in Natural Language Processing - Copenhagen, Denmark Duration: 7 Sept 2017 → 11 Sept 2017 http://emnlp2017.net/index.html http://emnlp2017.net/ |
Conference
Conference | EMNLP 2017: Conference on Empirical Methods in Natural Language Processing |
---|---|
Abbreviated title | EMNLP 2017 |
Country/Territory | Denmark |
City | Copenhagen |
Period | 7/09/17 → 11/09/17 |
Internet address |