Attributable and Scalable Opinion Summarization
This addresses the problem of generating attributable and scalable summaries from customer reviews for applications like product analysis, though it is incremental as it builds on existing latent space methods.
The authors tackled unsupervised opinion summarization by encoding review sentences into a hierarchical discrete latent space to identify common opinions, generating both abstractive and extractive summaries that are more informative and better grounded than prior work, as shown in evaluations on two datasets.
We propose a method for unsupervised opinion summarization that encodes sentences from customer reviews into a hierarchical discrete latent space, then identifies common opinions based on the frequency of their encodings. We are able to generate both abstractive summaries by decoding these frequent encodings, and extractive summaries by selecting the sentences assigned to the same frequent encodings. Our method is attributable, because the model identifies sentences used to generate the summary as part of the summarization process. It scales easily to many hundreds of input reviews, because aggregation is performed in the latent space rather than over long sequences of tokens. We also demonstrate that our appraoch enables a degree of control, generating aspect-specific summaries by restricting the model to parts of the encoding space that correspond to desired aspects (e.g., location or food). Automatic and human evaluation on two datasets from different domains demonstrates that our method generates summaries that are more informative than prior work and better grounded in the input reviews.