Neural keyphrase generation models have recently attracted interest in their ability to output absent keyphrases . In this paper, we discuss the usefulness of absentkeyphrase from an Information Retrieval (IR) perspective . We introduce a finer-grained categorization scheme that sheds light on the impact on scientific document retrieval . We find that only a fraction (around 20%) of the words that serve as document expansion actually serves as a document expansion, but that this small fraction of words is behind much of the gains observed in retrievaleffectiveness . We also discuss how the proposed scheme can offer a new angle toevaluate the output of neural keyphrasegeneration models .

Author(s) : Florian Boudin, Ygor Gallina

Links : PDF - Abstract

Code :

Keywords : retrieval - document - scheme - fraction - neural -

Leave a Reply

Your email address will not be published. Required fields are marked *