Disentangling Specificity for Abstractive Multi-document Summarization
This work addresses the challenge of generating comprehensive summaries from multiple documents for applications like news aggregation or research synthesis, though it appears incremental by building on existing MDS approaches.
The paper tackles the problem of multi-document summarization by addressing the neglect of document-specific information, which limits summary comprehensiveness, and proposes disentangling specific content using an orthogonal constraint, resulting in improved performance as shown through extensive analysis.
Multi-document summarization (MDS) generates a summary from a document set. Each document in a set describes topic-relevant concepts, while per document also has its unique contents. However, the document specificity receives little attention from existing MDS approaches. Neglecting specific information for each document limits the comprehensiveness of the generated summaries. To solve this problem, in this paper, we propose to disentangle the specific content from documents in one document set. The document-specific representations, which are encouraged to be distant from each other via a proposed orthogonal constraint, are learned by the specific representation learner. We provide extensive analysis and have interesting findings that specific information and document set representations contribute distinctive strengths and their combination yields a more comprehensive solution for the MDS. Also, we find that the common (i.e. shared) information could not contribute much to the overall performance under the MDS settings. Implemetation codes are available at https://github.com/congboma/DisentangleSum.