Visually and Phonologically Similar Characters in Incorrect Chinese Words: Analyses, Identification, and Applications

  title={Visually and Phonologically Similar Characters in Incorrect Chinese Words: Analyses, Identification, and Applications},
  author={C.-L. Liu and Min-Hua Lai and Kan-Wen Tien and Yi-Hsuan Chuang and Shi Hui Wu and C.-Y. Lee},
  journal={ACM Trans. Asian Lang. Inf. Process.},
Information about students’ mistakes opens a window to an understanding of their learning processes, and helps us design effective course work to help students avoid replication of the same errors. Learning from mistakes is important not just in human learning activities; it is also a crucial ingredient in techniques for the developments of student models. In this article, we report findings of our study on 4,100 erroneous Chinese words. Seventy-six percent of these errors were related to the… 

Applications of GPC Rules and Character Structures in Games for Learning Chinese Characters

Results of a preliminary evaluation of the games indicated significant improvement in learners' response times in Chinese naming tasks and a Web-based open system for teachers to prepare their own games to best meet their teaching goals was constructed.

The Effect of Visual Mnemonics and the Presentation of Character Pairs on Learning Visually Similar Characters for Chinese-As-Second-Language Learners

This study investigates the effects of visual mnemonics and the methods of presenting learning materials on learning visually similar characters for Chinese-as-second-language (CSL) learners. In

PHMOSpell: Phonological and Morphological Knowledge Guided Chinese Spelling Check

A novel end-to-end trainable model called PHMOSpell is proposed, which promotes the performance of CSC with multi-modal information by derive pinyin and glyph representations for Chinese characters from audio and visual modalities respectively, which are integrated into a pre-trained language model by a well-designed adaptive gating mechanism.

Read, Listen, and See: Leveraging Multimodal Information Helps Chinese Spell Checking

The REALISE model tackles the CSC task by capturing the semantic, phonetic and graphic information of the input characters, and selectively mixing the information in these modalities to predict the correct output.

Chinese Spelling Error Detection and Correction Based on Language Model, Pronunciation, and Shape

This work uses character-level n-gram language model to detect potential misspelled characters with low probabilities below some predefined threshold and generates a candidate set based on pronunciation and shape similarities for each potential incorrect character.

Correcting Chinese Spelling Errors with Word Lattice Decoding

A word lattice decoding model is developed for a Chinese spell checker that performs word segmentation and error correction simultaneously, thereby solving the word boundary problem and proposed methodology to extract spelling error samples automatically from the Google web 1T corpus.

Chunk-based Chinese Spelling Check with Global Optimization

This work proposes a chunk-based framework to correct single-character and multi-character word errors uniformly, and adopts a global optimization strategy to enable a sentence-level correction selection.

Integrating Dictionary and Web N-grams for Chinese Spell Checking

This work proposes a novel method for detecting and correcting Chinese typographical errors that achieves significantly better accuracy in error detection and more satisfactory performance in error correction than the state-of-the-art systems.

A Hybrid Approach to Automatic Corpus Generation for Chinese Spelling Check

This paper proposes a novel approach of constructing CSC corpus with automatically generated spelling errors, which are either visually or phonologically resembled characters, corresponding to the OCR- and ASR-based methods, respectively.

Chinese Spelling Checker Based on an Inverted Index List with a Rescoring Mechanism

An approach is proposed for Chinese spelling error detection and correction, in which an inverted index list with a rescoring mechanism is used, which achieved acceptable performance in terms of recall rate or precision rate in error sentence detection and error location detection.



Visually and Phonologically Similar Characters in Incorrect Simplified Chinese Words

This work collected 621 incorrect Chinese words reported on the Internet, and analyzed the causes of these errors, finding that phonologically and visually similar characters are major contributing factors for errors in Chinese text.

Phonological and Logographic Influences on Errors in Written Chinese Words

Experimental results show that using Web-based statistics can help to correct only about 75% of reported errors of Chinese words, and Web- based statistics are useful for recommending incorrect characters for composing test items for "incorrect character identification" tests about 93% of the time.

Visual and phonological pathways to the lexicon: Evidence from Chinese readers

It is concluded that visual information plays a greater role in Chinese character recognition than has previously been documented.

Using Structural Information for Identifying Similar Chinese Characters

Methods for identifying visually similar Chinese characters by adopting and extending the basic concepts of a proven Chinese input method--Cangjie are proposed.

Capturing Errors in Written Chinese Words

Experimental results show that using intuitive Web-based statistics helped to capture only about 75% of errors observed in writings of middle school students, which are useful for recommending incorrect characters for composing test items for "incorrect character identification" tests.

Role of structure and component in judgments of visual similarity of Chinese characters.

  • S. YehJing-Ling Li
  • Psychology
    Journal of experimental psychology. Human perception and performance
  • 2002
It is demonstrated that character structure plays a greater role in the visual similarity of Chinese characters than has been considered.

A cognition-based interactive game platform for learning Chinese characters

This work built interactive games for computer assisted learning of Chinese characters and collected and analyzed errors in written Chinese characters, and found that phonologically related factors also participated in a large proportion of the reported errors.

Phonology Matters: The Phonological Frequency Effect in Written Chinese

A universal phonological principle is pointed to according to which phonological information is routinely activated as a part of word identification, which suggests that part of the classic word-frequency effect may be phonological.

Two Applications of Lexical Information to Computer-Assisted Item Authoring for Elementary Chinese

Applying information implicitly contained in a machine readable lexicon, the system offers semantically and lexically similar words to help teachers prepare test items for cloze tests and furnishes quality recommendations for the preparation of test items, in addition to expediting the process.

Similarity Calculation of Chinese Character Glyph and its Application in Computer Aided Proofreading System

Experiment indicates that the similar character lists of 6763 characters in GB2312 calculated by this algorithm have a high coincidence with human perception, which improves the modification guide for users.