Improving Keyphrase Extraction with Data Augmentation and Information Filtering
This work addresses the problem of extracting keyphrases from informal texts like video transcripts for NLP applications, representing an incremental advance by adapting existing methods to a less-explored domain.
The paper tackles keyphrase extraction from informal video transcripts by proposing a novel data augmentation method to incorporate background knowledge from other domains, achieving effectiveness as demonstrated through extensive experiments on a new dataset from the Behance platform.
Keyphrase extraction is one of the essential tasks for document understanding in NLP. While the majority of the prior works are dedicated to the formal setting, e.g., books, news or web-blogs, informal texts such as video transcripts are less explored. To address this limitation, in this work we present a novel corpus and method for keyphrase extraction from the transcripts of the videos streamed on the Behance platform. More specifically, in this work, a novel data augmentation is proposed to enrich the model with the background knowledge about the keyphrase extraction task from other domains. Extensive experiments on the proposed dataset dataset show the effectiveness of the introduced method.