Neural Extractive Summarization with Side Information
This work addresses the challenge of improving summarization quality for newswire articles by leveraging often-available side information, representing an incremental advancement in the field.
The paper tackled the problem of single-document extractive summarization by incorporating side information like titles and image captions, showing that this approach consistently outperforms methods without side information in terms of informativeness and fluency on a large-scale news dataset.
Most extractive summarization methods focus on the main body of the document from which sentences need to be extracted. However, the gist of the document may lie in side information, such as the title and image captions which are often available for newswire articles. We propose to explore side information in the context of single-document extractive summarization. We develop a framework for single-document summarization composed of a hierarchical document encoder and an attention-based extractor with attention over side information. We evaluate our model on a large scale news dataset. We show that extractive summarization with side information consistently outperforms its counterpart that does not use any side information, in terms of both informativeness and fluency.