Words without Boundaries: Computational Approaches to Chinese Word Segmentation

The fact that words are not conventionally demarcated in Chinese orthography makes the process of word segmentation non-trivial. Chinese word segmentation remains a challenging topic in Chinese computational linguistics. We survey previous approaches to Chinese word segmentation, including dictionary look-up, strength of internal binding, as well as character tagging and machine learning. The Word Boundary Decision (WBD) approach which requires no prior lexical knowledge is proposed. It is shown that the WBD model greatly reduces the complexity of Chinese word segmentation and may provide a promising approach to address domain adaption and robustness issues.

• Publication year

  2012

• Venue

  Language and Linguistics Compass

• Publication date

  2012-08-01

• Fields of study

  Linguistics, Computer Science

• Identifiers
  DOI 10.1002/LNC3.357
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Apply Normalized Accessor Variety in Chinese Word Segmentation

  2010cited by this paper
• Chinese Word Segmentation Based on Word Boundary Decision

  2010cited by this paper
• Unsupervised Segmentation Helps Supervised Learning of Character Tagging for Word Segmentation and Named Entity Recognition

  2008cited by this paper
• The Penn Chinese TreeBank: Phrase structure annotation of a large corpus

  2005cited by this paper
• The Second International Chinese Word Segmentation Bakeoff

  2005cited by this paper
• Chinese Word Segmentation as Character Tagging

  2003cited by this paper
• On Chinese Language Processing

  2003cited by this paper
• Statistically-Enhanced New Word Identification in a Rule-Based Chinese System

  2000cited by this paper
• A corpus-based analysis of Mandarin nominal root compound

  1996cited by this paper
• Statistical Models for Word Segmentation And Unknown Word Resolution

  1992cited by this paper
• A statistical method for finding word boundaries in Chinese text

  1990cited by this paper

• Revisiting Chinese modality types: A collostructional approach to post-modal verbs

  2025cites this paper
• Word Boundary Decision: An Efficient Approach for Low-Resource Word Segmentation

  2024cites this paper
• Chinese word segmentation with heterogeneous graph convolutional network

  2024cites this paper
• Natural Language Processing Methods for Symbolic Music Generation and Information Retrieval: A Survey

  2024cites this paper
• Using Google Classroom to Increase Students Motivation to Learn English at SMP Negeri 1 Limboto Gorontalo

  2022cites this paper
• Regional varieties and diachronic changes in Chinese political discourse

  2022cites this paper
• Wordhood and Disyllabicity in Chinese

  2020influential citation
• Linguistic characteristics of Chinese register based on the Menzerath - Altmann law and text clustering

  2019cites this paper
• Tracking and recognizing emotions in short text messages from online chatting services

  2018cites this paper
• Word intuition agreement among Chinese speakers: a Mechanical Turk-based study

  2017cites this paper
• Finding Something to Read: Intelligibility, Readability and Learner Chinese Texts

  2017cites this paper
• Co-occurrence statistics as a language-dependent cue for speech segmentation.

  2017cites this paper
• The Digital Archive of Buddhist Temple Gazetteers and Named Entity Recognition (NER) in classical Chinese

  2015influential citation
• Chinese Word Segmentation for Agriculture

  2013cites this paper
• Active Learning for Chinese Word Segmentation

  2012cites this paper