Match More, Extract Better! Hybrid Matching Model for Open Domain Web Keyphrase Extraction

Keyphrase extraction aims to automatically extract salient phrases representing the critical information in the source document. Identifying salient phrases is challenging because there is a lot of noisy information in the document, leading to wrong extraction. To address this issue, in this paper, we propose a hybrid matching model for keyphrase extraction, which combines representation-focused and interactionbased matching modules into a unified framework for improving the performance of the keyphrase extraction task. Specifically, Hybrid-Match comprises (1) a PLM-based Siamese encoder component that represents both candidate phrases and documents, (2) an interactionfocused matching (IM) component that estimates word matches between candidate phrases and the corresponding document at the word level, and (3) a representation-focused matching (RM) component captures context-aware semantic relatedness of each candidate keyphrase at the phrase level. Extensive experimental results on the OpenKP dataset demonstrate that the performance of the proposed model Hybrid-Match outperforms the recent state-of-the-art keyphrase extraction baselines. Furthermore, we discuss the performance of large language models in keyphrase extraction based on recent studies and our experiments. Introduction Keyphrase Extraction (KE) is a fundamental task in natural language processing that aims to identify a series of salient and representative phrases relevant to the primary information discussed in a source document. Specifically, as shown in Table 1, keyphrases are concise content that encapsulates the central semantic meaning of a longer text (Hasan and Ng, 2014; Song et al., 2023b). Keyphrases play a crucial role in various natural * Corresponding Author The Input Document: Home of the Top Heavy Pizza Sandwiches Welcome 54 Pizza Express offers a high quality homemade product served with friendly efficient service for Dinein Carry out or Delivery Every 54 Pizza Express pizza is a quality pizza made with wholesome quality ingredients fresh vegetables delectable meats rich tangy tomato sauce and creamy mozzarella cheese Made fresh daily and served with your choice of dressing Choose from a Side Salad Dinner Salad Chef Salad Griled Chicken Salad Tuna Salad Buffalo Grilled Chicken Salad or Pepperoni and ... ... offer a high quality homemade product served with friendly efficient service for Dinein Carry out or Delivery Every 54 Pizza Express pizza is a quality pizza made with wholesome quality ingredient fresh vegetables delectable meats rich tangy tomato sauce and creamy mozzarella cheese At 54 Pizza Express we provide quality you can afford and a taste ...