Joao Lucas de Sousa Almeida, Arthur Cancelieri Pires, et al.
IEEE Transactions on Artificial Intelligence
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.
Joao Lucas de Sousa Almeida, Arthur Cancelieri Pires, et al.
IEEE Transactions on Artificial Intelligence
Béni Egressy, Luc von Niederhäusern, et al.
AAAI 2024
Naoki Abe, Kathleen Buckingham, et al.
KDD 2023
Oliver Bodemer
IBM J. Res. Dev