Delexicalized Paraphrase Generation

Boya Yu, Konstantine Arkoudas, Wael Hamza


Abstract
We present a neural model for paraphrasing and train it to generate delexicalized sentences. We achieve this by creating training data in which each input is paired with a number of reference paraphrases. These sets of reference paraphrases represent a weak type of semantic equivalence based on annotated slots and intents. To understand semantics from different types of slots, other than anonymizing slots, we apply convolutional neural networks (CNN) prior to pooling on slot values and use pointers to locate slots in the output. We show empirically that the generated paraphrases are of high quality, leading to an additional 1.29% exact match on live utterances. We also show that natural language understanding (NLU) tasks, such as intent classification and named entity recognition, can benefit from data augmentation using automatically generated paraphrases.
Anthology ID:
2020.coling-industry.10
Volume:
Proceedings of the 28th International Conference on Computational Linguistics: Industry Track
Month:
December
Year:
2020
Address:
Online
Editors:
Ann Clifton, Courtney Napoles
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
102–112
Language:
URL:
https://aclanthology.org/2020.coling-industry.10
DOI:
10.18653/v1/2020.coling-industry.10
Bibkey:
Cite (ACL):
Boya Yu, Konstantine Arkoudas, and Wael Hamza. 2020. Delexicalized Paraphrase Generation. In Proceedings of the 28th International Conference on Computational Linguistics: Industry Track, pages 102–112, Online. International Committee on Computational Linguistics.
Cite (Informal):
Delexicalized Paraphrase Generation (Yu et al., COLING 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-2/2020.coling-industry.10.pdf