- Patent Title: Device for generating aligned corpus based on unsupervised-learning alignment, method thereof, device for analyzing destructive expression morpheme using aligned corpus, and method for analyzing morpheme thereof
-
Application No.: US15026275Application Date: 2014-08-27
-
Publication No.: US10282413B2Publication Date: 2019-05-07
- Inventor: Chang Jin Ji
- Applicant: SYSTRAN INTERNATIONAL CO., LTD.
- Applicant Address: KR Seoul
- Assignee: SYSTRAN INTERNATIONAL CO., LTD.
- Current Assignee: SYSTRAN INTERNATIONAL CO., LTD.
- Current Assignee Address: KR Seoul
- Agency: Lex IP Meister, PLLC
- Priority: KR10-2013-0118062 20131002
- International Application: PCT/KR2014/007959 WO 20140827
- International Announcement: WO2015/050321 WO 20150409
- Main IPC: G06F17/27
- IPC: G06F17/27 ; G06F17/30 ; G06N99/00

Abstract:
Disclosed is a device for generating an aligned corpus based on unsupervised-learning alignment, and a method thereof, a device for analyzing a destructive expression morpheme using an aligned corpus, and a method for analyzing a morpheme thereof.The morpheme analyzing device includes a knowledge database and an analyzer. The knowledge database includes an aligned corpus for storing a plurality of knowledge information sets used for a per-language morpheme analysis, and stores a morpheme dictionary for storing morpheme information corresponding to a normal expression and normal expression information corresponding to a destructive expression (here, the destructive expression represents an expression that is erroneous in orthography or is not normalized and standardized). The analyzer performs a morpheme analysis on an input separate word by use of the knowledge database and outputs an analysis result, and when a morpheme on the input separate word is not provided in the morpheme dictionary, finds a normal expression corresponding to the destructive expression by use of the aligned corpus regarding the destructive expression included in the input separate word, and performs a morpheme analysis.
Public/Granted literature
Information query