Comparative Snippet Generation

Saurabh Jain, Yisong Miao, Min-Yen Kan


Abstract
We model products’ reviews to generate comparative responses consisting of positive and negative experiences regarding the product. Specifically, we generate a single-sentence, comparative response from a given positive and a negative opinion. We contribute the first dataset for this task of Comparative Snippet Generation from contrasting opinions regarding a product, and an analysis of performance of a pre-trained BERT model to generate such snippets.
Anthology ID:
2022.ecnlp-1.7
Volume:
Proceedings of the Fifth Workshop on e-Commerce and NLP (ECNLP 5)
Month:
May
Year:
2022
Address:
Dublin, Ireland
Editors:
Shervin Malmasi, Oleg Rokhlenko, Nicola Ueffing, Ido Guy, Eugene Agichtein, Surya Kallumadi
Venue:
ECNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
49–57
Language:
URL:
https://aclanthology.org/2022.ecnlp-1.7
DOI:
10.18653/v1/2022.ecnlp-1.7
Bibkey:
Cite (ACL):
Saurabh Jain, Yisong Miao, and Min-Yen Kan. 2022. Comparative Snippet Generation. In Proceedings of the Fifth Workshop on e-Commerce and NLP (ECNLP 5), pages 49–57, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
Comparative Snippet Generation (Jain et al., ECNLP 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.ecnlp-1.7.pdf
Video:
 https://aclanthology.org/2022.ecnlp-1.7.mp4
Code
 wing-nus/comparative-snippet-generation-dataset
Data
SPOT