Leveraging Locality in Abstractive Text Summarization

Yixin Liu, Ansong Ni, Linyong Nan, Budhaditya Deb, Chenguang Zhu, Ahmed Hassan Awadallah, Dragomir Radev


Abstract
Neural attention models have achieved significant improvements on many natural language processing tasks. However, the quadratic memory complexity of the self-attention module with respect to the input length hinders their applications in long text summarization. Instead of designing more efficient attention modules, we approach this problem by investigating if models with a restricted context can have competitive performance compared with the memory-efficient attention models that maintain a global context by treating the input as a single sequence. Our model is applied to individual pages, which contain parts of inputs grouped by the principle of locality, during both the encoding and decoding stages. We empirically investigated three kinds of locality in text summarization at different levels of granularity, ranging from sentences to documents. Our experimental results show that our model has a better performance compared with strong baseline models with efficient attention modules, and our analysis provides further insights into our locality-aware modeling strategy.
Anthology ID:
2022.emnlp-main.408
Volume:
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
6081–6093
Language:
URL:
https://aclanthology.org/2022.emnlp-main.408
DOI:
10.18653/v1/2022.emnlp-main.408
Bibkey:
Cite (ACL):
Yixin Liu, Ansong Ni, Linyong Nan, Budhaditya Deb, Chenguang Zhu, Ahmed Hassan Awadallah, and Dragomir Radev. 2022. Leveraging Locality in Abstractive Text Summarization. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 6081–6093, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
Leveraging Locality in Abstractive Text Summarization (Liu et al., EMNLP 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.emnlp-main.408.pdf