KERT: Automatic Extraction and Ranking of Topical Keyphrases from Content-Representative Document Titles
This work addresses the need for better keyphrase extraction in academic domains, though it appears incremental as it builds on existing unsupervised methods with a new ranking approach.
The paper tackled the problem of extracting and ranking topical keyphrases from document titles by introducing KERT, a phrase-centric framework that shifts from unigram-based methods, resulting in improved performance on Computer Science and Physics datasets.
We introduce KERT (Keyphrase Extraction and Ranking by Topic), a framework for topical keyphrase generation and ranking. By shifting from the unigram-centric traditional methods of unsupervised keyphrase extraction to a phrase-centric approach, we are able to directly compare and rank phrases of different lengths. We construct a topical keyphrase ranking function which implements the four criteria that represent high quality topical keyphrases (coverage, purity, phraseness, and completeness). The effectiveness of our approach is demonstrated on two collections of content-representative titles in the domains of Computer Science and Physics.