Mind The Facts: Knowledge-Boosted Coherent Abstractive Text Summarization
This work addresses factuality and coherence issues in abstractive text summarization, which is important for applications like news aggregation, but it is incremental as it builds on existing Transformer architectures.
The authors tackled the problem of neural abstractive summarization models often producing factually inaccurate and incoherent summaries, especially for long articles, by incorporating entity-level knowledge from Wikidata and Transformer-XL techniques, resulting in improved ROUGE scores on the CNN/Daily Mail dataset.
Neural models have become successful at producing abstractive summaries that are human-readable and fluent. However, these models have two critical shortcomings: they often don't respect the facts that are either included in the source article or are known to humans as commonsense knowledge, and they don't produce coherent summaries when the source article is long. In this work, we propose a novel architecture that extends Transformer encoder-decoder architecture in order to improve on these shortcomings. First, we incorporate entity-level knowledge from the Wikidata knowledge graph into the encoder-decoder architecture. Injecting structural world knowledge from Wikidata helps our abstractive summarization model to be more fact-aware. Second, we utilize the ideas used in Transformer-XL language model in our proposed encoder-decoder architecture. This helps our model with producing coherent summaries even when the source article is long. We test our model on CNN/Daily Mail summarization dataset and show improvements on ROUGE scores over the baseline Transformer model. We also include model predictions for which our model accurately conveys the facts, while the baseline Transformer model doesn't.