A novel emerging topic detection method: A knowledge ecology perspective

Yang, Jinqing; Lu, Wei; Hu, Jiming; Huang, Shengzhi

doi:10.1016/j.ipm.2021.102843

Cited by 9 publications

(2 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As important metadata summarizing the core contents of a document, keyphrases are intended to index a document and enable readers quickly to find it and identify whether or not it is relevant to their specific needs or interests, which can also help to improve the visibility and influence of the documents (Gbur & Trumbo, 1995; Hartley & Kostoff, 2003; Turney, 2002). Meanwhile, because of their high importance and abstractness in the documents, keyphrases are also regarded as a suitable representation of topics, concepts, and knowledge, and are widely used for topic evolution study, knowledge mining, information retrieval, text summarization, and other NLP tasks (Cheng et al, 2020; Firoozeh et al, 2020; Hernandez‐Castaneda et al, 2020; Hu et al, 2019; K. Lu & Kipp, 2014; W. Lu et al, 2019, 2021; Sesagiri Raamkumar et al, 2017; Sun et al, 2020; Yang et al, 2022; Yoon et al, 2018). Owing to the importance and good performance of keyphrases regarding these tasks, automatic keyphrases prediction, including keyphrase extraction and generation, based on different algorithms, has attracted extensive attention (Çano & Bojar, 2019; Hasan & Ng, 2014).…”

Section: Introductionmentioning

confidence: 99%

“…Meanwhile, because of their high importance and abstractness in the documents, keyphrases are also regarded as a suitable representation of topics, concepts, and knowledge, and are widely used for topic evolution study, knowledge mining, information retrieval, text summarization, and other NLP tasks (Cheng et al, 2020;Firoozeh et al, 2020;Hernandez-Castaneda et al, 2020;Hu et al, 2019; K. Lu & Kipp, 2014;W. Lu et al, 2019Sesagiri Raamkumar et al, 2017;Sun et al, 2020;Yang et al, 2022;Yoon et al, 2018). Owing to the importance and good performance of keyphrases regarding these tasks, automatic keyphrases prediction, including keyphrase extraction and generation, based on different algorithms, has attracted extensive attention (Çano & Bojar, 2019;Hasan & Ng, 2014).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Generating keyphrases for readers: A controllable keyphrase generation framework

Jiang

Meng

Huang

et al. 2023

Asso for Info Science & Tech

Self Cite

View full text Add to dashboard Cite

With the wide application of keyphrases in many Information Retrieval (IR) and Natural Language Processing (NLP) tasks, automatic keyphrase prediction has been emerging. However, these statistically important phrases are contributing increasingly less to the related tasks because the end‐to‐end learning mechanism enables models to learn the important semantic information of the text directly. Similarly, keyphrases are of little help for readers to quickly grasp the paper's main idea because the relationship between the keyphrase and the paper is not explicit to readers. Therefore, we propose to generate keyphrases with specific functions for readers to bridge the semantic gap between them and the information producers, and verify the effectiveness of the keyphrase function for assisting users’ comprehension with a user experiment. A controllable keyphrase generation framework (the CKPG) that uses the keyphrase function as a control code to generate categorized keyphrases is proposed and implemented based on Transformer, BART, and T5, respectively. For the Computer Science domain, the Macro‐avgs of P@5, R@5, and F1@5 on the Paper with Code dataset are up to 0.680, 0.535, and 0.558, respectively. Our experimental results indicate the effectiveness of the CKPG models.

show abstract