Abstract
Aiming to generate a set of keyphrases, Keyphrase Generation (KG) is a classical task for capturing the central idea from a given document. Based on Seq2Seq models, the previous reinforcement learning framework on KG tasks utilizes the evaluation metrics to further improve the well-trained neural models. However, these KG evaluation metrics such as F1@5 and F1@M are only aware of the exact correctness of predictions on phrase-level and ignore the semantic similarities between similar predictions and targets, which inhibits the model from learning deep linguistic patterns. In response to this problem, we propose a new fine-grained evaluation metric to improve the RL framework, which considers different granularities: token-level F1 score, edit distance, duplication, and prediction quantities. On the whole, the new framework includes two reward functions: the fine-grained evaluation score and the vanilla F1 score. This framework helps the model identifying some partial match phrases which can be further optimized as the exact match ones. Experiments on KG benchmarks show that our proposed training framework outperforms the previous RL training frameworks among all evaluation scores. In addition, our method can effectively ease the synonym problem and generate a higher quality prediction. The source code is available at https://github.com/xuyige/FGRL4KG.- Anthology ID:
- 2021.findings-emnlp.45
- Volume:
- Findings of the Association for Computational Linguistics: EMNLP 2021
- Month:
- November
- Year:
- 2021
- Address:
- Punta Cana, Dominican Republic
- Editors:
- Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
- Venue:
- Findings
- SIG:
- SIGDAT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 497–507
- Language:
- URL:
- https://aclanthology.org/2021.findings-emnlp.45
- DOI:
- 10.18653/v1/2021.findings-emnlp.45
- Cite (ACL):
- Yichao Luo, Yige Xu, Jiacheng Ye, Xipeng Qiu, and Qi Zhang. 2021. Keyphrase Generation with Fine-Grained Evaluation-Guided Reinforcement Learning. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 497–507, Punta Cana, Dominican Republic. Association for Computational Linguistics.
- Cite (Informal):
- Keyphrase Generation with Fine-Grained Evaluation-Guided Reinforcement Learning (Luo et al., Findings 2021)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-3/2021.findings-emnlp.45.pdf
- Code
- xuyige/fgrl4kg
- Data
- KP20k