Unsupervised Opinion Summarization Using Approximate Geodesics

Somnath Basu Roy Chowdhury, Nicholas Monath, Kumar Dubey, Amr Ahmed, Snigdha Chaturvedi


Abstract
Opinion summarization is the task of creating summaries capturing popular opinions from user reviews. In this paper, we introduce Geodesic Summarizer (GeoSumm), a novel system to perform unsupervised extractive opinion summarization. GeoSumm consists of an encoder-decoder based representation learning model that generates topical representations of texts. These representations capture the underlying semantics of the text as a distribution over learnable latent units. GeoSumm generates these topical representations by performing dictionary learning over pre-trained text representations at multiple layers of the decoder. We then use these topical representations to quantify the importance of review sentences using a novel approximate geodesic distance-based scoring mechanism. We use the importance scores to identify popular opinions in order to compose general and aspect-specific summaries. Our proposed model, GeoSumm, achieves strong performance on three opinion summarization datasets. We perform additional experiments to analyze the functioning of our model and showcase the generalization ability of GeoSumm across different domains.
Anthology ID:
2023.findings-emnlp.8
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2023
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
97–112
Language:
URL:
https://aclanthology.org/2023.findings-emnlp.8
DOI:
10.18653/v1/2023.findings-emnlp.8
Bibkey:
Cite (ACL):
Somnath Basu Roy Chowdhury, Nicholas Monath, Kumar Dubey, Amr Ahmed, and Snigdha Chaturvedi. 2023. Unsupervised Opinion Summarization Using Approximate Geodesics. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 97–112, Singapore. Association for Computational Linguistics.
Cite (Informal):
Unsupervised Opinion Summarization Using Approximate Geodesics (Basu Roy Chowdhury et al., Findings 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.findings-emnlp.8.pdf