Chinese Word Segmentation as Character Tagging

By Nianwen Xu. 2003

469 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

A Survey on Neural Speech Synthesis (2021, methodology): “For character-based languages such as Chinese, word segmentation [394, 444, 261] is necessary to detect the word boundary from raw text, which is important to ensure the accuracy for later POS tagging, prosody prediction, and grapheme-to-phoneme conversion process.”
Max-Margin Tensor Neural Network for Chinese Word Segmentation (2014, background): “The most popular approach treats word segmentation as a sequence labeling problem which was ﬁrst proposed in Xue (2003).”
Neural Word Segmentation with Rich Pretraining (2017, methodology): “For the former, we follow prior methods (Xue et al., 2003; Pei et al., 2014), using ﬁve-character window For the latter, we follow recent work (Chen et al., 2015b; Zhang et al., 2016b), using a bi-directional LSTM to encode input character sequence.”
Joint CTC/attention decoding for end-to-end speech recognition (2017, methodology): “…is applied to Japanese and Mandarin ASR tasks, which require extra linguistic resources including morphological analyzer (Kudo et al., 2004) or word segmentation (Xue et al., 2003) in addition to pronunciation dictionary to provide accurate lexicon and language models in conventional DNN/HMM ASR.”
Deep Learning for Chinese Word Segmentation and POS Tagging (2013, background): “The character-based tagging solution was first proposed in (Xue, 2003). This work caused quite a number of character position tagging based CWS studies because known and unknown words can be treated in the same way. Peng, Feng and McCallum (2004) first introduced a linear-chain CRFs model to the cha”
Syntactic Processing Using the Generalized Perceptron and Beam Search (2011, methodology): “Examples include Xue (2003), Peng, Feng, and McCallum (2004), and Wang et al. (2006), which use maximum entropy and conditional random ﬁeld models, and Jiang et al. (2008), which uses the perceptron model.”
Semi-Supervised Learning for Natural Language (2005, methodology): “Other variants of BIO tagging allocate a new tag for the last word of a segment and another tag for single-token segments (Xue, 2003).”
Chinese NER Using Lattice LSTM (2018, unknown): “1557 senting segmentation (Xue, 2003).”
Hybrid CTC/Attention Architecture for End-to-End Speech Recognition (2017, methodology): “Then, the method is further applied to Japanese and Mandarin ASR tasks, which require extra linguistic resources including a morphological analyzer [3] or word segmentation [21] in addition to a pronunciation dictionary to provide accurate lexicon and language models in conventional DNN/HMM ASR.”