Bidirectional LSTM-CRF Attention-based Model for Chinese Word Segmentation
This work addresses a fundamental problem in Chinese NLP, but it appears incremental as it combines existing techniques like LSTM, CRF, and attention.
The paper tackles Chinese word segmentation by proposing a Bidirectional LSTM-CRF Attention-based Model, which outperforms baseline neural network methods on PKU and MSRA benchmark datasets.
Chinese word segmentation (CWS) is the basic of Chinese natural language processing (NLP). The quality of word segmentation will directly affect the rest of NLP tasks. Recently, with the artificial intelligence tide rising again, Long Short-Term Memory (LSTM) neural network, as one of easily modeling in sequence, has been widely utilized in various kinds of NLP tasks, and functions well. Attention mechanism is an ingenious method to solve the memory compression problem on LSTM. Furthermore, inspired by the powerful abilities of bidirectional LSTM models for modeling sequence and CRF model for decoding, we propose a Bidirectional LSTM-CRF Attention-based Model in this paper. Experiments on PKU and MSRA benchmark datasets show that our model performs better than the baseline methods modeling by other neural networks.