Learning Rich Representation of Keyphrases from Text
Mayank Kulkarni, Debanjan Mahata, Ravneet Arora, Rajarshi Bhowmik
Abstract
In this work, we explore how to train task-specific language models aimed towards learning rich representation of keyphrases from text documents. We experiment with different masking strategies for pre-training transformer language models (LMs) in discriminative as well as generative settings. In the discriminative setting, we introduce a new pre-training objective - Keyphrase Boundary Infilling with Replacement (KBIR), showing large gains in performance (upto 8.16 points in F1) over SOTA, when the LM pre-trained using KBIR is fine-tuned for the task of keyphrase extraction. In the generative setting, we introduce a new pre-training setup for BART - KeyBART, that reproduces the keyphrases related to the input text in the CatSeq format, instead of the denoised original input. This also led to gains in performance (upto 4.33 points in F1@M) over SOTA for keyphrase generation. Additionally, we also fine-tune the pre-trained language models on named entity recognition (NER), question answering (QA), relation extraction (RE), abstractive summarization and achieve comparable performance with that of the SOTA, showing that learning rich representation of keyphrases is indeed beneficial for many other fundamental NLP tasks.- Anthology ID:
- 2022.findings-naacl.67
- 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:
- 891–906
- Language:
- URL:
- https://aclanthology.org/2022.findings-naacl.67
- DOI:
- 10.18653/v1/2022.findings-naacl.67
- Cite (ACL):
- Mayank Kulkarni, Debanjan Mahata, Ravneet Arora, and Rajarshi Bhowmik. 2022. Learning Rich Representation of Keyphrases from Text. In Findings of the Association for Computational Linguistics: NAACL 2022, pages 891–906, Seattle, United States. Association for Computational Linguistics.
- Cite (Informal):
- Learning Rich Representation of Keyphrases from Text (Kulkarni et al., Findings 2022)
- PDF:
- https://preview.aclanthology.org/naacl-24-ws-corrections/2022.findings-naacl.67.pdf
- Code
- bloomberg/kbir_keybart
- Data
- Inspec, KP20k, SQuAD