arxivst stuff from arxiv that you should probably bookmark

Semi-supervised Multitask Learning for Sequence Labeling

Abstract · Apr 24, 2017 11:47 ·

word language sequence pos labeling entity tokens objective modeling cs-cl cs-lg cs-ne

Arxiv Abstract

  • Marek Rei

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.

Read the paper (pdf) »