TY - GEN
T1 - Low resource sequence tagging using sentence reconstruction
AU - Perl, Tal
AU - Chaudhury, Sriram
AU - Giryes, Raja
N1 - Publisher Copyright:
© 2020 Association for Computational Linguistics
PY - 2020
Y1 - 2020
N2 - This work revisits the task of training sequence tagging models with limited resources using transfer learning. We investigate several proposed approaches introduced in recent works and suggest a new loss that relies on sentence reconstruction from normalized embeddings. Specifically, our method demonstrates how by adding a decoding layer for sentence reconstruction, we can improve the performance of various baselines. We show improved results on the CoNLL02 NER and UD 1.2 POS datasets and demonstrate the power of the method for transfer learning with low-resources achieving 0.6 F1 score in Dutch using only one sample from it. The code is publicly available at: https://github.com/tperl/Low-Resource-Sequence-Tagging-using-Sentence-Reconstruction.
AB - This work revisits the task of training sequence tagging models with limited resources using transfer learning. We investigate several proposed approaches introduced in recent works and suggest a new loss that relies on sentence reconstruction from normalized embeddings. Specifically, our method demonstrates how by adding a decoding layer for sentence reconstruction, we can improve the performance of various baselines. We show improved results on the CoNLL02 NER and UD 1.2 POS datasets and demonstrate the power of the method for transfer learning with low-resources achieving 0.6 F1 score in Dutch using only one sample from it. The code is publicly available at: https://github.com/tperl/Low-Resource-Sequence-Tagging-using-Sentence-Reconstruction.
UR - http://www.scopus.com/inward/record.url?scp=85104009165&partnerID=8YFLogxK
U2 - 10.18653/v1/2020.acl-main.239
DO - 10.18653/v1/2020.acl-main.239
M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???
AN - SCOPUS:85104009165
T3 - Proceedings of the Annual Meeting of the Association for Computational Linguistics
SP - 2692
EP - 2698
BT - ACL 2020 - 58th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference
PB - Association for Computational Linguistics (ACL)
T2 - 58th Annual Meeting of the Association for Computational Linguistics, ACL 2020
Y2 - 5 July 2020 through 10 July 2020
ER -