Semi-supervised Multitask Learning for Sequence Labeling
This incremental approach benefits NLP practitioners by enhancing performance on tasks like error detection and named entity recognition.
The paper tackled sequence labeling tasks by introducing a secondary language modeling objective to predict surrounding words, which improved accuracy across multiple benchmarks without extra data.
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.