Research Area:  Machine Learning
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.
Keywords:  
Keyphrase Generation
Fine-Grained
Reinforcement Learning
Seq2Seq models
Deep Learning
Machine Learning
Author(s) Name:  Yichao Luo, Yige Xu, Jiacheng Ye, Xipeng Qiu, Qi Zhang
Journal name:  Computer Science
Conferrence name:  
Publisher name:  arXiv:2104.08799
DOI:  10.48550/arXiv.2104.08799
Volume Information:  
Paper Link:   https://arxiv.org/abs/2104.08799