SentBS: Sentence-level Beam Search for Controllable Summarization

Chenhui Shen, Liying Cheng, Lidong Bing, Yang You, Luo Si


Abstract
A wide range of control perspectives have been explored in controllable text generation. Structure-controlled summarization is recently proposed as a useful and interesting research direction. However, current structure-controlling methods have limited effectiveness in enforcing the desired structure. To address this limitation, we propose a sentence-level beam search generation method (SentBS), where evaluation is conducted throughout the generation process to select suitable sentences for subsequent generations. We experiment with different combinations of decoding methods to be used as sub-components by SentBS and evaluate results on the structure-controlled dataset MReD. Experiments show that all explored combinations for SentBS can improve the agreement between the generated text and the desired structure, with the best method significantly reducing the structural discrepancies suffered by the existing model, by approximately 68%.
Anthology ID:
2022.emnlp-main.699
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:
10256–10265
Language:
URL:
https://aclanthology.org/2022.emnlp-main.699
DOI:
10.18653/v1/2022.emnlp-main.699
Bibkey:
Cite (ACL):
Chenhui Shen, Liying Cheng, Lidong Bing, Yang You, and Luo Si. 2022. SentBS: Sentence-level Beam Search for Controllable Summarization. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 10256–10265, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
SentBS: Sentence-level Beam Search for Controllable Summarization (Shen et al., EMNLP 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.emnlp-main.699.pdf