Semantic Extractor-Paraphraser based Abstractive Summarization
This work addresses the need for better automatic summarization in text-heavy environments, though it appears incremental by building on existing extractor-paraphraser approaches.
The authors tackled abstractive summarization by proposing a semantic extractor-paraphraser model that outperforms state-of-the-art baselines in ROUGE, METEOR, and word mover similarity metrics.
The anthology of spoken languages today is inundated with textual information, necessitating the development of automatic summarization models. In this manuscript, we propose an extractor-paraphraser based abstractive summarization system that exploits semantic overlap as opposed to its predecessors that focus more on syntactic information overlap. Our model outperforms the state-of-the-art baselines in terms of ROUGE, METEOR and word mover similarity (WMS), establishing the superiority of the proposed system via extensive ablation experiments. We have also challenged the summarization capabilities of the state of the art Pointer Generator Network (PGN), and through thorough experimentation, shown that PGN is more of a paraphraser, contrary to the prevailing notion of a summarizer; illustrating it's incapability to accumulate information across multiple sentences.