@inproceedings{nguyen-nguyen-2021-phonlp,
title = "{P}ho{NLP}: A joint multi-task learning model for {V}ietnamese part-of-speech tagging, named entity recognition and dependency parsing",
author = "Nguyen, Linh The and
Nguyen, Dat Quoc",
editor = "Sil, Avi and
Lin, Xi Victoria",
booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Demonstrations",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.naacl-demos.1",
doi = "10.18653/v1/2021.naacl-demos.1",
pages = "1--7",
abstract = "We present the first multi-task learning model {--} named PhoNLP {--} for joint Vietnamese part-of-speech (POS) tagging, named entity recognition (NER) and dependency parsing. Experiments on Vietnamese benchmark datasets show that PhoNLP produces state-of-the-art results, outperforming a single-task learning approach that fine-tunes the pre-trained Vietnamese language model PhoBERT (Nguyen and Nguyen, 2020) for each task independently. We publicly release PhoNLP as an open-source toolkit under the Apache License 2.0. Although we specify PhoNLP for Vietnamese, our PhoNLP training and evaluation command scripts in fact can directly work for other languages that have a pre-trained BERT-based language model and gold annotated corpora available for the three tasks of POS tagging, NER and dependency parsing. We hope that PhoNLP can serve as a strong baseline and useful toolkit for future NLP research and applications to not only Vietnamese but also the other languages. Our PhoNLP is available at \url{https://github.com/VinAIResearch/PhoNLP}",
}
Markdown (Informal)
[PhoNLP: A joint multi-task learning model for Vietnamese part-of-speech tagging, named entity recognition and dependency parsing](https://aclanthology.org/2021.naacl-demos.1) (Nguyen & Nguyen, NAACL 2021)
ACL