Semi-supervised Multitask Learning for Sequence Labeling

Understand

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.