One Size Does Not Fit All: Generating and Evaluating Variable Number of Keyphrases

Xingdi Yuan, Tong Wang, Rui Meng, Khushboo Thaker, Peter Brusilovsky, Daqing He, Adam Trischler


Abstract
Different texts shall by nature correspond to different number of keyphrases. This desideratum is largely missing from existing neural keyphrase generation models. In this study, we address this problem from both modeling and evaluation perspectives. We first propose a recurrent generative model that generates multiple keyphrases as delimiter-separated sequences. Generation diversity is further enhanced with two novel techniques by manipulating decoder hidden states. In contrast to previous approaches, our model is capable of generating diverse keyphrases and controlling number of outputs. We further propose two evaluation metrics tailored towards the variable-number generation. We also introduce a new dataset StackEx that expands beyond the only existing genre (i.e., academic writing) in keyphrase generation tasks. With both previous and new evaluation metrics, our model outperforms strong baselines on all datasets.
Anthology ID:
2020.acl-main.710
Volume:
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2020
Address:
Online
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
7961–7975
Language:
URL:
https://aclanthology.org/2020.acl-main.710
DOI:
10.18653/v1/2020.acl-main.710
Bibkey:
Cite (ACL):
Xingdi Yuan, Tong Wang, Rui Meng, Khushboo Thaker, Peter Brusilovsky, Daqing He, and Adam Trischler. 2020. One Size Does Not Fit All: Generating and Evaluating Variable Number of Keyphrases. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 7961–7975, Online. Association for Computational Linguistics.
Cite (Informal):
One Size Does Not Fit All: Generating and Evaluating Variable Number of Keyphrases (Yuan et al., ACL 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.acl-main.710.pdf
Video:
 http://slideslive.com/38929166
Code
 memray/OpenNMT-kpg-release
Data
STACKEXKP20k