Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
METHOD AND APPARATUS FOR WORD SEGMENTATION
Document Type and Number:
WIPO Patent Application WO/2020/052069
Kind Code:
A1
Abstract:
A method and apparatus (500) for word segmentation, said method comprising: acquiring a pre-determined word set and a text to be segmented (201), the pre-determined word set being a word set generated in advance on the basis of a pre-determined text set, and words in the pre-determined word set comprising first information and second information; performing word segmentation on said text on the basis of the pre-determined word set, so as to obtain at least one word sequence (202); determining first information and second information about words in a word sequence in at least one word sequence, and determining the probability of the word sequence on the basis of the determined first information and second information (203), the second information about the word in the word sequence being second information determined on the basis of a word adjacent to the word; selecting, from at least one word sequence, a word sequence having the largest probability as a word segmentation result (204). The method and apparatus improve the accuracy of the word segmentation.

More Like This:
WO/2017/180475QUERY OPTIMIZER FOR COMBINED STRUCTURED AND UNSTRUCTURED DATA RECORDS
JP2004118740QUESTION ANSWERING SYSTEM, QUESTION ANSWERING METHOD AND QUESTION ANSWERING PROGRAM
WO/2012/059854SUGGESTING RELEVANT TERMS DURING TEXT ENTRY
Inventors:
DENG JIANGDONG (CN)
Application Number:
PCT/CN2018/116345
Publication Date:
March 19, 2020
Filing Date:
November 20, 2018
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
BEIJING BYTEDANCE NETWORK TECH CO LTD (CN)
International Classes:
G06F17/27
Foreign References:
CN106610937A2017-05-03
CN108038103A2018-05-15
CN104899190A2015-09-09
CN104375989A2015-02-25
US20140309986A12014-10-16
Other References:
JIANG JIANHONG ET AL: "Analysis and application of Chinese word segmentation model which consist of dictionary and statistics method", COMPUTER ENGINEERING AND DESIGN, vol. 33, no. 1, 31 January 2012 (2012-01-31), pages 387 - 391, XP055691070, ISSN: 1000-7024, DOI: :10.16208/j.issn1000-7024.2012.01.034
Attorney, Agent or Firm:
INSIGHT INTELLECTUAL PROPERTY LIMITED (CN)
Download PDF:
View/Download PDF      PDF Help



 
Previous Patent: METHOD AND DEVICE FOR DETERMINING GEOMETRIC TRANSFORMATION RELATIONSHIP BETWEEN IMAGES

Next Patent: CONTINUOUS NANOMETER TIO2 SURFACE TREATMENT METHOD