Semantic Extractor-Paraphraser based Abstractive Summarization

Anubhav Jangra, Raghav Jain, Vaibhav Mavi, Sriparna Saha, Pushpak Bhattacharyya


Abstract
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.
Anthology ID:
2020.icon-main.25
Volume:
Proceedings of the 17th International Conference on Natural Language Processing (ICON)
Month:
December
Year:
2020
Address:
Indian Institute of Technology Patna, Patna, India
Editors:
Pushpak Bhattacharyya, Dipti Misra Sharma, Rajeev Sangal
Venue:
ICON
SIG:
Publisher:
NLP Association of India (NLPAI)
Note:
Pages:
191–199
Language:
URL:
https://aclanthology.org/2020.icon-main.25
DOI:
Bibkey:
Cite (ACL):
Anubhav Jangra, Raghav Jain, Vaibhav Mavi, Sriparna Saha, and Pushpak Bhattacharyya. 2020. Semantic Extractor-Paraphraser based Abstractive Summarization. In Proceedings of the 17th International Conference on Natural Language Processing (ICON), pages 191–199, Indian Institute of Technology Patna, Patna, India. NLP Association of India (NLPAI).
Cite (Informal):
Semantic Extractor-Paraphraser based Abstractive Summarization (Jangra et al., ICON 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.icon-main.25.pdf