Applying a Generic Sequence-to-Sequence Model for Simple and Effective Keyphrase Generation
This provides a simpler, easier-to-deploy solution for researchers and practitioners needing keyphrase extraction from text, though it is incremental.
The authors tackled keyphrase generation by adapting the BART seq2seq model with a simple training procedure, achieving results comparable to state-of-the-art systems on five benchmarks.
In recent years, a number of keyphrase generation (KPG) approaches were proposed consisting of complex model architectures, dedicated training paradigms and decoding strategies. In this work, we opt for simplicity and show how a commonly used seq2seq language model, BART, can be easily adapted to generate keyphrases from the text in a single batch computation using a simple training procedure. Empirical results on five benchmarks show that our approach is as good as the existing state-of-the-art KPG systems, but using a much simpler and easy to deploy framework.