SETA- Extractive to Abstractive Summarization with a Similarity-Based Attentional Encoder-Decoder Model

Abstract

Summarizing information provided within tables of scientific documents has always been a problem. A system that can summarize this vital information, which a table encapsulates, can provide readers with a quick and straightforward solution to comprehend the contents of the document. To train such systems, we need data, and finding a quality one is tricky. To mitigate this challenge, we developed a high-quality corpus that contains both extractive and abstractive summaries derived from tables, using a rule-based approach. This dataset was validated using a combination of automated and manual metrics. Subsequently, we developed a novel Encoder-Decoder framework, along with attention, to generate abstractive summaries from extractive ones. This model works on a mix of extractive summaries and inter-sentential similarity embeddings and learns to map them to corresponding abstractive summaries. On experimentation, we discovered that our model addresses the saliency factor of summarization, an aspect overlooked by previous works. Further experiments show that our model develops coherent abstractive summaries, validated by high BLEU and ROUGE scores.