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%.
BibTeX
@inproceedings{shen-etal-2022-sentbs,
title = "{S}ent{BS}: Sentence-level Beam Search for Controllable Summarization",
author = "Shen, Chenhui and
Cheng, Liying and
Bing, Lidong and
You, Yang and
Si, Luo",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.emnlp-main.699/",
doi = "10.18653/v1/2022.emnlp-main.699",
pages = "10256--10265"
}