Amr Ahmed


2023

pdf
Unsupervised Opinion Summarization Using Approximate Geodesics
Somnath Basu Roy Chowdhury | Nicholas Monath | Kumar Dubey | Amr Ahmed | Snigdha Chaturvedi
Proceedings of the 4th New Frontiers in Summarization Workshop

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.

pdf
Unsupervised Opinion Summarization Using Approximate Geodesics
Somnath Basu Roy Chowdhury | Nicholas Monath | Kumar Dubey | Amr Ahmed | Snigdha Chaturvedi
Findings of the Association for Computational Linguistics: EMNLP 2023

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.

2010

pdf
Staying Informed: Supervised and Semi-Supervised Multi-View Topical Analysis of Ideological Perspective
Amr Ahmed | Eric Xing
Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing