A Timestep aware Sentence Embedding and Acme Coverage for Brief but Informative Title Generation

Quanbin Wang, XieXiong Lin, Feng Wang


Abstract
The title generation task that summarizes article content in recapitulatory words relies heavily on utilizing the corresponding key context. To generate a title with appropriate information in the content and avoid repetition, we propose a title generation framework with two complementary components in this paper. First, we propose a Timestep aware Sentence Embedding (TSE) mechanism, which updates the sentences’ representations by re-locating the critical words in the corresponding sentence for each decoding step. Then, we present an Acme Coverage (AC) mechanism to solve the repetition problem and preserve the remaining valuable keywords after each decoding step according to the final vocabulary distribution. We conduct comprehensive experiments on various title generation tasks with different backbones, the evaluation scores of ROUGE and METEOR in varying degrees are significantly outperforming most of the existing state-of-the-art approaches. The experimental results demonstrate the effectiveness and generality of our novel generation framework TSE-AC.
Anthology ID:
2022.findings-naacl.146
Volume:
Findings of the Association for Computational Linguistics: NAACL 2022
Month:
July
Year:
2022
Address:
Seattle, United States
Editors:
Marine Carpuat, Marie-Catherine de Marneffe, Ivan Vladimir Meza Ruiz
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1906–1918
Language:
URL:
https://aclanthology.org/2022.findings-naacl.146
DOI:
10.18653/v1/2022.findings-naacl.146
Bibkey:
Cite (ACL):
Quanbin Wang, XieXiong Lin, and Feng Wang. 2022. A Timestep aware Sentence Embedding and Acme Coverage for Brief but Informative Title Generation. In Findings of the Association for Computational Linguistics: NAACL 2022, pages 1906–1918, Seattle, United States. Association for Computational Linguistics.
Cite (Informal):
A Timestep aware Sentence Embedding and Acme Coverage for Brief but Informative Title Generation (Wang et al., Findings 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.findings-naacl.146.pdf
Code
 alipay/timestep-aware-sentenceembedding-and-acmecoverage
Data
AESLC