Interpretable Multi-headed Attention for Abstractive Summarization at Controllable Lengths

Ritesh Sarkhel, Moniba Keymanesh, Arnab Nandi, Srinivasan Parthasarathy


Abstract
Abstractive summarization at controllable lengths is a challenging task in natural language processing. It is even more challenging for domains where limited training data is available or scenarios in which the length of the summary is not known beforehand. At the same time, when it comes to trusting machine-generated summaries, explaining how a summary was constructed in human-understandable terms may be critical. We propose Multi-level Summarizer (MLS), a supervised method to construct abstractive summaries of a text document at controllable lengths. The key enabler of our method is an interpretable multi-headed attention mechanism that computes attention distribution over an input document using an array of timestep independent semantic kernels. Each kernel optimizes a human-interpretable syntactic or semantic property. Exhaustive experiments on two low-resource datasets in English show that MLS outperforms strong baselines by up to 14.70% in the METEOR score. Human evaluation of the summaries also suggests that they capture the key concepts of the document at various length-budgets.
Anthology ID:
2020.coling-main.606
Volume:
Proceedings of the 28th International Conference on Computational Linguistics
Month:
December
Year:
2020
Address:
Barcelona, Spain (Online)
Editors:
Donia Scott, Nuria Bel, Chengqing Zong
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
6871–6882
Language:
URL:
https://aclanthology.org/2020.coling-main.606
DOI:
10.18653/v1/2020.coling-main.606
Bibkey:
Cite (ACL):
Ritesh Sarkhel, Moniba Keymanesh, Arnab Nandi, and Srinivasan Parthasarathy. 2020. Interpretable Multi-headed Attention for Abstractive Summarization at Controllable Lengths. In Proceedings of the 28th International Conference on Computational Linguistics, pages 6871–6882, Barcelona, Spain (Online). International Committee on Computational Linguistics.
Cite (Informal):
Interpretable Multi-headed Attention for Abstractive Summarization at Controllable Lengths (Sarkhel et al., COLING 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.coling-main.606.pdf