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}.
The Chinese University of Hong Kong(香港中文大学);Shenzhen Research Institute, The Chinese University of Hong Kong(香港中文大学深圳研究院);Department of Computer Science and EngineeringThe Chinese University of Hong Kong(香港中文大学计算机科学与工程学系)
AraGenre 2026: A Hierarchical Definition-Guided Arabic Genre Classification Shared Task
VinUniversity(温大);Lancaster University(兰卡斯特大学);King Fahd University of Petroleum and Minerals(法赫德国王石油与矿产大学);Onaizah Colleges(欧奈宰学院);University College of Applied Sciences(应用科学大学学院);Hamad Bin Khalifa University(哈马德·本·哈利法大学)
Exploring Optical-Flow-Guided Motion and Detection-Based Appearance for Temporal Sentence Grounding
Wangxuan Institute of Computer Technology, Peking University(北京大学王选计算机研究所);School of Cyber Science and Engineering, Huazhong University of Science and Technology(华中科技大学网络空间安全学院)
Seed-Guided Fine-Grained Entity Typing in Science and Engineering Domains
University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);IBM Thomas J. Watson Research Center(IBM托马斯·J·沃森研究中心);IBM Almaden Research Center(IBM阿尔马登研究中心)
Multi-Grained Query-Guided Set Prediction Network for Grounded Multimodal Named Entity Recognition
School of Artificial Intelligence, Sun Yat-sen University(中山大学人工智能学院);School of Atmospheric Sciences, Sun Yat-sen University(中山大学大气科学学院);School of Electronics and Communication Engineering, Sun Yat-sen University(中山大学电子与通信工程学院);State Key Laboratory of Intelligent Game, Institute of Software, Chinese Academy of Sciences(中国科学院软件研究所智能游戏国家重点实验室);Pazhou Lab(琶洲实验室)