Unlock instant, AI-driven research and patent intelligence for your innovation.

Inner-text personal pronoun anaphora resolution method based on semantic features

A semantic feature and referential resolution technology, applied in the fields of information system modeling and knowledge engineering, can solve problems such as inability to effectively reduce manual dependence and poor quality, and achieve the effect of stable referential resolution performance.

Active Publication Date: 2015-03-25
JIANGSU JINGE NETWORK TECH
View PDF3 Cites 29 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the quality of the preliminary ontology automatically constructed by computer programs is usually very poor, which cannot effectively reduce the dependence on manual work, so manual construction is still the mainstream method

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
  • Inner-text personal pronoun anaphora resolution method based on semantic features
  • Inner-text personal pronoun anaphora resolution method based on semantic features

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0025] Embodiment 1, a personal pronoun reference resolution method based on semantic features in a text, firstly identify the characters in the text; secondly extract the semantic features of the characters; select the candidate pronouns again; finally calculate the referential relationship between the pronouns and the candidate characters To determine the referent of a pronoun, the specific steps are as follows:

[0026] A: Character recognition: Preprocessing the text, the preprocessing includes: word segmentation, named entity recognition, part-of-speech tagging; for the processed text, determine the position of the person (including names and pronouns) in the text; its operation steps as follows:

[0027] A1: Segment the text, including part-of-speech tagging;

[0028] A2: Sequentially extract character words whose parts of speech are marked as nr (representing person’s name) and r (representing pronoun), and determine the position of character words in the text;

[002...

Embodiment 2

[0039] Embodiment 2, with reference to figure 1 , an operation experiment of a semantic feature-based personal pronoun reference resolution method in text, the steps are as follows:

[0040] Step 01: Person identification. Preprocessing the text, the preprocessing includes: word segmentation, named entity recognition, part-of-speech tagging; for the processed text, determine the position of characters (including names and pronouns) in the text.

[0041] Step 02: Semantic feature extraction. For the identified characters, according to their respective sentence and paragraph information, extract semantic related words, and construct the semantic features of names and pronouns.

[0042] Step 03: Candidate selection. Filter the gender, singular and plural, and distance of names and pronouns, and select a number of qualified candidates for pronouns.

[0043] Step 04: Referential relationship calculation. Calculate the semantic feature correlation between the pronoun and the ca...

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 discloses an inner-text personal pronoun anaphora resolution method based on semantic features. The inner-text personal pronoun anaphora resolution method includes the following specific steps: (1) carrying out person identification, wherein a text is preprocessed, the preprocessing steps include paragraph and statement identification, named entity identification and work characteristic labeling, and as for the processed text, the positions of persons and the positions of pronouns in the text are determined; (2) extracting the semantic features, wherein semantic associated words are extracted from the identified persons and the identified pronouns according to information of statements where the persons and the pronouns are located and information of paragraphs where the persons and the pronouns are located, and the semantic features of person names and the pronouns are built; (3) selecting candidates, wherein the sexes, the singular and plural characteristics and the distances of the persons and the pronouns are filtered, and the multiple candidates meeting conditions are selected for the pronouns; (4) calculating an anaphora relation, wherein the semantic feature relevancy between the pronouns and the candidates is calculated, and the anaphora persons of the pronouns are determined in cooperation with the semantic feature relevancy and the distances between the persons and the pronouns. By means of the inner-text personal pronoun anaphora resolution method, inner-text personal pronoun anaphora resolution is achieved.

Description

technical field [0001] The invention belongs to the fields of information system modeling and knowledge engineering, in particular to a method for dissolving personal pronoun reference in text based on semantic features. Background technique [0002] With the rapid development of social informatization, the Internet has become an important source of information for people. However, network information has the characteristics of mass, complexity, and unstructured, which brings great difficulties to the acquisition of network information and the analysis and research work based on network information collection. The concept of ontology originated in the field of philosophy, which refers to the explanation and description of the objective existence system. In recent decades, it has developed rapidly in many fields such as artificial intelligence, computer science and knowledge engineering. Ontology can achieve a certain degree of knowledge sharing and reuse, making the compute...

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 仲兆满姜剑陈宗华陈永江乔磊
Owner JIANGSU JINGE NETWORK TECH