A new method of computing chinese word similarity based on statistics

Bo Zhang; Lei Hong; Shubin Song; Liang He; Guorong Li

doi:10.1109/BIFE.2012.17

A new method of computing chinese word similarity based on statistics

Bo Zhang
, Lei Hong
, Shubin Song
, Liang He^*
, Guorong Li

^*Corresponding author for this work

School of Computer Science and Technology

East China Normal University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Scopus citations

Abstract

Word semantic similarity is a very subjective concept and it is very difficult to get a similarity value close to human judgment. Chinese word semantic similarity research is relatively scarce due to its inherent complexity. This paper presents an approach to compute Chinese word semantic similarity based on statistical methods with word frequency contrast introduced (WFC-WS). Word semantic vectors are first obtained using co-occurrence and then extended with HIT-IR Tongyici Cilin (Extended). Word frequency contrast is introduced to filter the semantic vectors. Experiments show that the results of WFC-WS are closer to artificial standard compared with some similar methods.

Original language	English
Title of host publication	Proceedings of the 2012 5th International Conference on Business Intelligence and Financial Engineering, BIFE 2012
Pages	43-46
Number of pages	4
DOIs	https://doi.org/10.1109/BIFE.2012.17
State	Published - 2012
Event	2012 5th International Conference on Business Intelligence and Financial Engineering, BIFE 2012 - Lanzhou, Gansu, China Duration: 18 Aug 2012 → 21 Aug 2012

Publication series

Name	Proceedings of the 2012 5th International Conference on Business Intelligence and Financial Engineering, BIFE 2012

Conference

Conference	2012 5th International Conference on Business Intelligence and Financial Engineering, BIFE 2012
Country/Territory	China
City	Lanzhou, Gansu
Period	18/08/12 → 21/08/12

Keywords

Co-occurrence
Semantic similarity
Tongyici cilin

Access to Document

10.1109/BIFE.2012.17

Cite this

Zhang, B., Hong, L., Song, S., He, L., & Li, G. (2012). A new method of computing chinese word similarity based on statistics. In Proceedings of the 2012 5th International Conference on Business Intelligence and Financial Engineering, BIFE 2012 (pp. 43-46). Article 6305076 (Proceedings of the 2012 5th International Conference on Business Intelligence and Financial Engineering, BIFE 2012). https://doi.org/10.1109/BIFE.2012.17

@inproceedings{b61eea1220894aefb8620393653f35b0,

title = "A new method of computing chinese word similarity based on statistics",

abstract = "Word semantic similarity is a very subjective concept and it is very difficult to get a similarity value close to human judgment. Chinese word semantic similarity research is relatively scarce due to its inherent complexity. This paper presents an approach to compute Chinese word semantic similarity based on statistical methods with word frequency contrast introduced (WFC-WS). Word semantic vectors are first obtained using co-occurrence and then extended with HIT-IR Tongyici Cilin (Extended). Word frequency contrast is introduced to filter the semantic vectors. Experiments show that the results of WFC-WS are closer to artificial standard compared with some similar methods.",

keywords = "Co-occurrence, Semantic similarity, Tongyici cilin",

author = "Bo Zhang and Lei Hong and Shubin Song and Liang He and Guorong Li",

year = "2012",

doi = "10.1109/BIFE.2012.17",

language = "英语",

isbn = "9780769547503",

series = "Proceedings of the 2012 5th International Conference on Business Intelligence and Financial Engineering, BIFE 2012",

pages = "43--46",

booktitle = "Proceedings of the 2012 5th International Conference on Business Intelligence and Financial Engineering, BIFE 2012",

note = "2012 5th International Conference on Business Intelligence and Financial Engineering, BIFE 2012 ; Conference date: 18-08-2012 Through 21-08-2012",

}

Zhang, B, Hong, L, Song, S, He, L & Li, G 2012, A new method of computing chinese word similarity based on statistics. in Proceedings of the 2012 5th International Conference on Business Intelligence and Financial Engineering, BIFE 2012., 6305076, Proceedings of the 2012 5th International Conference on Business Intelligence and Financial Engineering, BIFE 2012, pp. 43-46, 2012 5th International Conference on Business Intelligence and Financial Engineering, BIFE 2012, Lanzhou, Gansu, China, 18/08/12. https://doi.org/10.1109/BIFE.2012.17

A new method of computing chinese word similarity based on statistics. / Zhang, Bo; Hong, Lei; Song, Shubin et al.
Proceedings of the 2012 5th International Conference on Business Intelligence and Financial Engineering, BIFE 2012. 2012. p. 43-46 6305076 (Proceedings of the 2012 5th International Conference on Business Intelligence and Financial Engineering, BIFE 2012).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - A new method of computing chinese word similarity based on statistics

AU - Zhang, Bo

AU - Hong, Lei

AU - Song, Shubin

AU - He, Liang

AU - Li, Guorong

PY - 2012

Y1 - 2012

N2 - Word semantic similarity is a very subjective concept and it is very difficult to get a similarity value close to human judgment. Chinese word semantic similarity research is relatively scarce due to its inherent complexity. This paper presents an approach to compute Chinese word semantic similarity based on statistical methods with word frequency contrast introduced (WFC-WS). Word semantic vectors are first obtained using co-occurrence and then extended with HIT-IR Tongyici Cilin (Extended). Word frequency contrast is introduced to filter the semantic vectors. Experiments show that the results of WFC-WS are closer to artificial standard compared with some similar methods.

AB - Word semantic similarity is a very subjective concept and it is very difficult to get a similarity value close to human judgment. Chinese word semantic similarity research is relatively scarce due to its inherent complexity. This paper presents an approach to compute Chinese word semantic similarity based on statistical methods with word frequency contrast introduced (WFC-WS). Word semantic vectors are first obtained using co-occurrence and then extended with HIT-IR Tongyici Cilin (Extended). Word frequency contrast is introduced to filter the semantic vectors. Experiments show that the results of WFC-WS are closer to artificial standard compared with some similar methods.

KW - Co-occurrence

KW - Semantic similarity

KW - Tongyici cilin

UR - https://www.scopus.com/pages/publications/84868094532

U2 - 10.1109/BIFE.2012.17

DO - 10.1109/BIFE.2012.17

M3 - 会议稿件

AN - SCOPUS:84868094532

SN - 9780769547503

T3 - Proceedings of the 2012 5th International Conference on Business Intelligence and Financial Engineering, BIFE 2012

SP - 43

EP - 46

BT - Proceedings of the 2012 5th International Conference on Business Intelligence and Financial Engineering, BIFE 2012

T2 - 2012 5th International Conference on Business Intelligence and Financial Engineering, BIFE 2012

Y2 - 18 August 2012 through 21 August 2012

ER -

Zhang B, Hong L, Song S, He L, Li G. A new method of computing chinese word similarity based on statistics. In Proceedings of the 2012 5th International Conference on Business Intelligence and Financial Engineering, BIFE 2012. 2012. p. 43-46. 6305076. (Proceedings of the 2012 5th International Conference on Business Intelligence and Financial Engineering, BIFE 2012). doi: 10.1109/BIFE.2012.17

A new method of computing chinese word similarity based on statistics

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this