Multi-Perspective Abstractive Answer Summarization
This work addresses the problem of summarizing diverse answers in forums like Stack Overflow for users seeking comprehensive insights, though it is incremental in advancing summarization techniques.
The paper tackled the lack of a dataset for multi-perspective abstractive answer summarization in community question answering forums by introducing an automatic dataset creation method and a multi-reward optimization technique, resulting in improved coverage of perspectives and faithfulness compared to a strong baseline.
Community Question Answering (CQA) forums such as Stack Overflow and Yahoo! Answers contain a rich resource of answers to a wide range of questions. Each question thread can receive a large number of answers with different perspectives. The goal of multi-perspective answer summarization is to produce a summary that includes all perspectives of the answer. A major obstacle for multi-perspective, abstractive answer summarization is the absence of a dataset to provide supervision for producing such summaries. This work introduces a novel dataset creation method to automatically create multi-perspective, bullet-point abstractive summaries from an existing CQA forum. Supervision provided by this dataset trains models to inherently produce multi-perspective summaries. Additionally, to train models to output more diverse, faithful answer summaries while retaining multiple perspectives, we propose a multi-reward optimization technique coupled with a sentence-relevance prediction multi-task loss. Our methods demonstrate improved coverage of perspectives and faithfulness as measured by automatic and human evaluations compared to a strong baseline.