Switch-LSTMs for Multi-Criteria Chinese Word Segmentation
This addresses the problem of segmenting Chinese text under multiple criteria for NLP applications, offering a flexible solution that transfers knowledge to new criteria, though it appears incremental in method.
The paper tackled multi-criteria Chinese word segmentation by proposing Switch-LSTMs, a model that uses multiple LSTMs and a switcher to route among sub-criteria, achieving significant improvements on eight corpora compared to previous methods.
Multi-criteria Chinese word segmentation is a promising but challenging task, which exploits several different segmentation criteria and mines their common underlying knowledge. In this paper, we propose a flexible multi-criteria learning for Chinese word segmentation. Usually, a segmentation criterion could be decomposed into multiple sub-criteria, which are shareable with other segmentation criteria. The process of word segmentation is a routing among these sub-criteria. From this perspective, we present Switch-LSTMs to segment words, which consist of several long short-term memory neural networks (LSTM), and a switcher to automatically switch the routing among these LSTMs. With these auto-switched LSTMs, our model provides a more flexible solution for multi-criteria CWS, which is also easy to transfer the learned knowledge to new criteria. Experiments show that our model obtains significant improvements on eight corpora with heterogeneous segmentation criteria, compared to the previous method and single-criterion learning.