TY - GEN

T1 - Jointly Learning to Label Sentences and Tokens

AU - Rei, Marek

AU - Søgaard, Anders

PY - 2019

Y1 - 2019

N2 - Learning to construct text representations in end-to-end systems can be difficult, as natural languages are highly compositional and task-specific annotated datasets are often limited in size. Methods for directly supervising language composition can allow us to guide the models based on existing knowledge, regularizing them towards more robust and interpretable representations. In this paper, we investigate how objectives at different granularities can be used to learn better language representations and we propose an architecture for jointly learning to label sentences and tokens. The predictions at each level are combined together using an attention mechanism, with token-level labels also acting as explicit supervision for composing sentence-level representations. Our experiments show that by learning to perform these tasks jointly on multiple levels, the model achieves substantial improvements for both sentence classification and sequence labeling.

AB - Learning to construct text representations in end-to-end systems can be difficult, as natural languages are highly compositional and task-specific annotated datasets are often limited in size. Methods for directly supervising language composition can allow us to guide the models based on existing knowledge, regularizing them towards more robust and interpretable representations. In this paper, we investigate how objectives at different granularities can be used to learn better language representations and we propose an architecture for jointly learning to label sentences and tokens. The predictions at each level are combined together using an attention mechanism, with token-level labels also acting as explicit supervision for composing sentence-level representations. Our experiments show that by learning to perform these tasks jointly on multiple levels, the model achieves substantial improvements for both sentence classification and sequence labeling.

U2 - 10.1609/aaai.v33i01.33016916

DO - 10.1609/aaai.v33i01.33016916

M3 - Article in proceedings

SN - 978-1-57735-809-1

SP - 6916

EP - 6923

BT - Proceedings of 33nd AAAI Conference on Artificial Intelligence, AAAI 2019

PB - AAAI Press

T2 - 33rd AAAI Conference on Artificial Intelligence - AAAI 2019

Y2 - 27 January 2019 through 1 February 2019

ER -