Neural Word Segmentation Learning for Chinese

Abstract

Most previous approaches to Chinese word segmentation formalize this problem as a character-based sequence labeling task so that only contextual information within fixed sized local windows and simple interactions between adjacent tags can be captured. In this paper, we propose a novel neural framework which thoroughly eliminates context windows and can utilize complete segmentation history. Our model employs a gated combination neural network over characters to produce distributed representations of word candidates, which are then given to a long shortterm memory (LSTM) language scoring model. Experiments on the benchmark datasets show that without the help of feature engineering as most existing approaches, our models achieve competitive or better performances with previous stateof-the-art methods.

Transition-Based Neural Word Segmentation

“…In contrast, we leverage both character embeddings and word embeddings for better accuracies. (Morita et al, 2015;Liu et al, 2016;Cai and Zhao, 2016), which are different from our work in the basic framework. For instance, Liu et al (2016) follow Andrew (2006) using a semi-CRF for structured inference.…”

Word-Context Character Embeddings for Chinese Word Segmentation

“…As shown in Table 4, pre-training with conventional skip-gram embeddings gives only small improvements, which is consistent as findings of previous work (Chen et al, 2015a;Ma and 2015; Cai and Zhao, 2016). Segmentation with self-training even shows accuracy drops on PKU and MSR.…”

Neural Networks Incorporating Unlabeled and Partially-labeled Data for Cross-domain Chinese Word Segmentation

“…The method of Chen et al [2015] is a character-based method and that of Cai and Zhao [2016] is a word-based method. The method of Cai et al [2017] is a new improved version of that by Cai and Zhao [2016]. The three methods do not use any unlabeled or partially-labeled data except source domain labeled data S l .…”

“…These tags may indicate the position of a character in the word [Xue, 2003] or represent the intervals between characters [Huang et al, 2007]. Recently, along with the development of deep learning methods, some neural network models [Chen et al, 2015;Cai and Zhao, 2016;Liu et al, 2016;Cai et al, 2017] have achieved great success in CWS tasks. Despite their enormous success, however, these methods still have limitations: they usually rely heavily on manually labeled training data.…”