Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Language morphological analyzer

A morphological and linguistic technology, applied in the field of analyzing natural language, which can solve problems such as inapplicability

Inactive Publication Date: 2007-07-04
FRANCE TELECOM R&D BEIJNG
View PDF0 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Publication 3 can only analyze compound words as input and generate morphosyntactic relations between morphemes in the compound word, which is not applicable when the input is text

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Language morphological analyzer
  • Language morphological analyzer
  • Language morphological analyzer

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0042] 1. Architecture of Chinese Morphological Analyzer

[0043] While the invention has embodiments in many different forms, it should be understood that particular embodiments are shown in the drawings and described in detail herein. to the specific embodiments shown and disclosed. Preferred embodiments of the present invention will now be described with reference to the accompanying drawings.

[0044] The method of the present invention is used for identifying and extracting the morphological words of the language from the text according to the predefined morphological word formation grammar by computer. The method includes: loading computer-readable rules of a morphological word-forming grammar; inputting text, and obtaining sentences from the input text according to punctuation marks of the language; forming a lattice for each sentence, the lattice comprising at least one elements, each of which corresponds to a character or a possible word in the sentence; the lattice...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention provides a natural language morphological analyzer and a identifying and extracting MDW method from said language according to the MDW constituent grammar, said method includes following steps: loading the computer readable rules of MDW constituent grammar; inputting text and gaining sentence from the input text; forming the word format of every sentence, said word format at least includes one element, every element is corresponding with one word or one phase; analyzing the word format of every sentence by analytical algorithm combined with loaded MDW constituent grammar to gain MDW alternative word from one or several elements; outputting gained MDW alternative word. The invention can identify and extract MDW from text effectively, and gain the syntax, semantic and shape model information.

Description

technical field [0001] The present invention relates to a technology for analyzing natural language, in particular to a method for recognizing and extracting morphological words (Morphologically Derived Word, MDW) from text and a device using the method. Background technique [0002] Automatic recognition and extraction of morphological words (hereinafter referred to as MDW) is the premise of Natural Language Processing (NLP). Morphological analysis is used for word segmentation, information retrieval (IR), machine translation (MT), text-to-speech (TTS) and other NLP applications. For example, in the field of IR, if a person searches for content associated with "shower" on the Internet, traditional search engines can only obtain content containing "shower". However, a large number of contents related to "take a bath", "take a bath" and the like of the MDW as "take a bath" cannot be obtained. Therefore, it is very important to identify and extract MDW. [0003] The morphol...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06F17/27
Inventor 毛新年李珩董远
Owner FRANCE TELECOM R&D BEIJNG
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products