TY - GEN
T1 - Self-training for unsupervised parsing with PRPN
AU - Mohananey, Anhad
AU - Kann, Katharina
AU - Bowman, Samuel R.
N1 - Publisher Copyright:
© 2020 Association for Computational Linguistics.
PY - 2020
Y1 - 2020
N2 - Neural unsupervised parsing (UP) models learn to parse without access to syntactic annotations, while being optimized for another task like language modeling. In this work, we propose self-training for neural UP models: we leverage aggregated annotations predicted by copies of our model as supervision for future copies. To be able to use our model's predictions during training, we extend a recent neural UP architecture, the PRPN (Shen et al., 2018a), such that it can be trained in a semi-supervised fashion. We then add examples with parses predicted by our model to our unlabeled UP training data. Our self-trained model outperforms the PRPN by 8.1% F1 and the previous state of the art by 1.6% F1. In addition, we show that our architecture can also be helpful for semi-supervised parsing in ultra-lowresource settings.
AB - Neural unsupervised parsing (UP) models learn to parse without access to syntactic annotations, while being optimized for another task like language modeling. In this work, we propose self-training for neural UP models: we leverage aggregated annotations predicted by copies of our model as supervision for future copies. To be able to use our model's predictions during training, we extend a recent neural UP architecture, the PRPN (Shen et al., 2018a), such that it can be trained in a semi-supervised fashion. We then add examples with parses predicted by our model to our unlabeled UP training data. Our self-trained model outperforms the PRPN by 8.1% F1 and the previous state of the art by 1.6% F1. In addition, we show that our architecture can also be helpful for semi-supervised parsing in ultra-lowresource settings.
UR - http://www.scopus.com/inward/record.url?scp=85113904171&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85113904171&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85113904171
T3 - Proceedings of the Annual Meeting of the Association for Computational Linguistics
SP - 105
EP - 110
BT - IWPT 2020 - 16th International Conference on Parsing Technologies and IWPT 2020 Shared Task on Parsing into Enhanced Universal Dependencies, Proceedings of the Conference
PB - Association for Computational Linguistics (ACL)
T2 - 16th International Conference on Parsing Technologies, IWPT 2020, co-located with the 58th Annual Meeting of the Association for Computational Linguistics, ACL 2020
Y2 - 9 July 2020
ER -