Does Order Matter? An Empirical Study on Generating Multiple Keyphrases as a Sequence

Abstract

Recently, concatenating multiple keyphrases as a target sequence has been proposed as a new learning paradigm for keyphrase generation. Existing studies concatenate target keyphrases in different orders but no study has examined the effects of ordering on models' behavior. In this paper, we propose several orderings for concatenation and inspect the important factors for training a successful keyphrase generation model. By running comprehensive comparisons, we observe one preferable ordering and summarize a number of empirical findings and challenges, which can shed light on future research on this line of work.

References in corpus (1)

• Keyphrase Generation: A Text Summarization Struggle

Cited by in corpus (7)

• Learning Dynamic Belief Graphs to Generalize on Text-Based Games
• TNT-KID: Transformer-based Neural Tagger for Keyword Identification
• Applying Transformer-based Text Summarization for Keyphrase Generation
• From Statistical Methods to Deep Learning, Automatic Keyphrase Prediction: A Survey
• Building Dynamic Knowledge Graphs from Text-based Games
• UniKeyphrase: A Unified Extraction and Generation Framework for Keyphrase Prediction
• One2Set: Generating Diverse Keyphrases as a Set