Unsupervised Boundary-Aware Language Model Pretraining for Chinese Sequence Labeling
This work addresses the need for reducing human effort in lexicon creation for Chinese NLP tasks, offering an incremental improvement by complementing existing supervised methods.
The paper tackled the problem of incorporating boundary information into Chinese sequence labeling tasks without relying on human-curated lexicons by proposing BABERT, an unsupervised method that encodes statistical boundary information into pre-trained language models, resulting in consistent improvements across ten benchmarks.
Boundary information is critical for various Chinese language processing tasks, such as word segmentation, part-of-speech tagging, and named entity recognition. Previous studies usually resorted to the use of a high-quality external lexicon, where lexicon items can offer explicit boundary information. However, to ensure the quality of the lexicon, great human effort is always necessary, which has been generally ignored. In this work, we suggest unsupervised statistical boundary information instead, and propose an architecture to encode the information directly into pre-trained language models, resulting in Boundary-Aware BERT (BABERT). We apply BABERT for feature induction of Chinese sequence labeling tasks. Experimental results on ten benchmarks of Chinese sequence labeling demonstrate that BABERT can provide consistent improvements on all datasets. In addition, our method can complement previous supervised lexicon exploration, where further improvements can be achieved when integrated with external lexicon information.