Robust Chinese Word Segmentation with Contextualized Word Representations
This work addresses a key bottleneck in Chinese NLP by reducing OOV errors, though it is incremental as it builds on existing neural methods.
The paper tackled the problem of high error rates for out-of-vocabulary words in Chinese word segmentation by using a bidirectional LSTM with a pretrained language model to generate contextualized character representations, achieving state-of-the-art performance on multiple datasets.
In recent years, after the neural-network-based method was proposed, the accuracy of the Chinese word segmentation task has made great progress. However, when dealing with out-of-vocabulary words, there is still a large error rate. We used a simple bidirectional LSTM architecture and a large-scale pretrained language model to generate high-quality contextualize character representations, which successfully reduced the weakness of the ambiguous meanings of each Chinese character that widely appears in Chinese characters, and hence effectively reduced OOV error rate. State-of-the-art performance is achieved on many datasets.