Comparative Study of Sentence Embeddings for Contextual Paraphrasing

Louisa Pragst, Wolfgang Minker, Stefan Ultes


Abstract
Paraphrasing is an important aspect of natural-language generation that can produce more variety in the way specific content is presented. Traditionally, paraphrasing has been focused on finding different words that convey the same meaning. However, in human-human interaction, we regularly express our intention with phrases that are vastly different regarding both word content and syntactic structure. Instead of exchanging only individual words, the complete surface realisation of a sentences is altered while still preserving its meaning and function in a conversation. This kind of contextual paraphrasing did not yet receive a lot of attention from the scientific community despite its potential for the creation of more varied dialogues. In this work, we evaluate several existing approaches to sentence encoding with regard to their ability to capture such context-dependent paraphrasing. To this end, we define a paraphrase classification task that incorporates contextual paraphrases, perform dialogue act clustering, and determine the performance of the sentence embeddings in a sentence swapping task.
Anthology ID:
2020.lrec-1.845
Volume:
Proceedings of the 12th Language Resources and Evaluation Conference
Month:
May
Year:
2020
Address:
Marseille, France
Venue:
LREC
SIG:
Publisher:
European Language Resources Association
Note:
Pages:
6841–6851
Language:
English
URL:
https://aclanthology.org/2020.lrec-1.845
DOI:
Bibkey:
Cite (ACL):
Louisa Pragst, Wolfgang Minker, and Stefan Ultes. 2020. Comparative Study of Sentence Embeddings for Contextual Paraphrasing. In Proceedings of the 12th Language Resources and Evaluation Conference, pages 6841–6851, Marseille, France. European Language Resources Association.
Cite (Informal):
Comparative Study of Sentence Embeddings for Contextual Paraphrasing (Pragst et al., LREC 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.lrec-1.845.pdf