Autores
Ta Hoang Thang
Rahman Abu Bakar Siddiqur
Gelbukh Alexander
Título GAN-BERT, an Adversarial Learning Architecture for Paraphrase Identification
Tipo Congreso
Sub-tipo Memoria
Descripción 2022 Iberian Languages Evaluation Forum, IberLEF 2022
Resumen In this paper, we address the task of Paraphrase Identification in Mexican Spanish (PAR-MEX) at sentence-level. We introduced our method, using text embeddings from pre-trained transformer models for the training process by GAN-BERT, an adversarial learning. We modified noises for the generator, which have a random rate and the same size of the hidden layer of transformers. To improve the model performance, a rule of thumb based on the pair similarity is used to remove possible wrong sentence pairs in positive examples; parallel with the addition of unlabelled data in the same domain. The best obtained F1 is 90.22%, ranked third in the final result table, also outperformed the organizers' baseline. © 2022 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).
Observaciones CEUR Workshop Proceedings, v. 3202
Lugar Coruña
País España
No. de páginas
Vol. / Cap.
Inicio 2022-09-20
Fin
ISBN/ISSN