Abstract
State-of-the-art keyphrase generation methods generally depend on large annotated datasets, limiting their performance in domains with limited annotated data. To overcome this challenge, we design a data-oriented approach that first identifies salient information using retrieval-based corpus-level statistics, and then learns a task-specific intermediate representation based on a pre-trained language model using large-scale unlabeled documents. We introduce salient span recovery and salient span prediction as denoising training objectives that condense the intra-article and inter-article knowledge essential for keyphrase generation. Through experiments on multiple keyphrase generation benchmarks, we show the effectiveness of the proposed approach for facilitating low-resource keyphrase generation and zero-shot domain adaptation. Our method especially benefits the generation of absent keyphrases, approaching the performance of models trained with large training sets.- Anthology ID:
- 2022.findings-emnlp.49
- Volume:
- Findings of the Association for Computational Linguistics: EMNLP 2022
- Month:
- December
- Year:
- 2022
- Address:
- Abu Dhabi, United Arab Emirates
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 700–716
- Language:
- URL:
- https://aclanthology.org/2022.findings-emnlp.49
- DOI:
- Cite (ACL):
- Di Wu, Wasi Ahmad, Sunipa Dev, and Kai-Wei Chang. 2022. Representation Learning for Resource-Constrained Keyphrase Generation. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 700–716, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
- Cite (Informal):
- Representation Learning for Resource-Constrained Keyphrase Generation (Wu et al., Findings 2022)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/2022.findings-emnlp.49.pdf