Semi-supervised multitask learning for sequence labeling
Published version
Peer-reviewed
Repository URI
Repository DOI
Change log
Authors
Rei, M
Abstract
We propose a sequence labeling framework with a secondary training objective, learning to predict surrounding words for every word in the dataset. This language modeling objective incentivises the system to learn general-purpose patterns of semantic and syntactic composition, which are also useful for improving accuracy on different sequence labeling tasks. The architecture was evaluated on a range of datasets, covering the tasks of error detection in learner texts, named entity recognition, chunking and POS-tagging. The novel language modeling objective provided consistent performance improvements on every benchmark, without requiring any additional annotated or unannotated data.
Description
Keywords
Journal Title
ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)
Conference Name
Proceedings of the 55th Annual Meeting of the Association for
Computational Linguistics (Volume 1: Long Papers)
Journal ISSN
Volume Title
1
Publisher
Association for Computational Linguistics
Publisher DOI
Sponsorship
Cambridge Assessment (unknown)