Keyphrase Generation with Fine-Grained Evaluation-Guided Reinforcement Learning

TL;DR

This paper introduces a fine-grained evaluation metric for keyphrase generation that considers semantic similarities and multiple granularities, improving reinforcement learning models' ability to generate higher quality keyphrases.

Contribution

It proposes a novel fine-grained evaluation metric and reinforcement learning framework that enhances keyphrase generation by capturing partial matches and semantic similarities.

Findings

Outperforms previous RL frameworks on benchmark datasets.

Eases the synonym problem in keyphrase generation.

Produces higher quality and more accurate keyphrases.

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 $F_1@5$ and $F_1@M$ 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 $F_1$ 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 $F_1$ 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 \url{https://github.com/xuyige/FGRL4KG}.