Opinion Summarization by Weak-Supervision from Mix-structured Data

Yizhu Liu, Qi Jia, Kenny Zhu


Abstract
Opinion summarization of multiple reviews suffers from the lack of reference summaries for training. Most previous approaches construct multiple reviews and their summary based on textual similarities between reviews,resulting in information mismatch between the review input and the summary. In this paper, we convert each review into a mixof structured and unstructured data, which we call opinion-aspect pairs (OAs) and implicit sentences (ISs).We propose a new method to synthesize training pairs of such mix-structured data as input and the textual summary as output,and design a summarization model with OA encoder and IS encoder. Experiments show that our approach outperforms previous methods on Yelp, Amazon and RottenTomatos datasets.
Anthology ID:
2022.emnlp-main.201
Volume:
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3086–3096
Language:
URL:
https://aclanthology.org/2022.emnlp-main.201
DOI:
10.18653/v1/2022.emnlp-main.201
Bibkey:
Cite (ACL):
Yizhu Liu, Qi Jia, and Kenny Zhu. 2022. Opinion Summarization by Weak-Supervision from Mix-structured Data. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 3086–3096, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
Opinion Summarization by Weak-Supervision from Mix-structured Data (Liu et al., EMNLP 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.emnlp-main.201.pdf