KATSum: Knowledge-aware Abstractive Text Summarization
This addresses the issue of generating unreliable summaries for users relying on automated text summarization, though it appears incremental as it builds on existing Seq2Seq methods with knowledge integration.
The authors tackled the problem of unfaithfulness and factual errors in abstractive text summarization by proposing KATSum, a model that integrates Knowledge Graph triplets into a Seq2Seq framework, which significantly reduced factual errors in summaries.
Text Summarization is recognised as one of the NLP downstream tasks and it has been extensively investigated in recent years. It can assist people with perceiving the information rapidly from the Internet, including news articles, social posts, videos, etc. Most existing research works attempt to develop summarization models to produce a better output. However, advent limitations of most existing models emerge, including unfaithfulness and factual errors. In this paper, we propose a novel model, named as Knowledge-aware Abstractive Text Summarization, which leverages the advantages offered by Knowledge Graph to enhance the standard Seq2Seq model. On top of that, the Knowledge Graph triplets are extracted from the source text and utilised to provide keywords with relational information, producing coherent and factually errorless summaries. We conduct extensive experiments by using real-world data sets. The results reveal that the proposed framework can effectively utilise the information from Knowledge Graph and significantly reduce the factual errors in the summary.