Shashanka Ubaru, Sanjeeb Dash, et al.
NeurIPS 2020
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.
Shashanka Ubaru, Sanjeeb Dash, et al.
NeurIPS 2020
Ella Barkan, Ibrahim Siddiqui, et al.
Computational And Structural Biotechnology Journal
Hiroki Yanagisawa, Kohei Miyaguchi, et al.
NeurIPS 2022
Bruce Elmegreen, Hendrik Hamann, et al.
ICR 2023