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

Demand entity co-reference detection method and device based on deep learning and context semantics

A technology of deep learning and detection methods, which is applied in the computer field to avoid insufficient annotation data resources.

Active Publication Date: 2020-11-17
INST OF SOFTWARE - CHINESE ACAD OF SCI
View PDF5 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0015] Aiming at the technical problems existing in the prior art, the purpose of the present invention is to propose a method and device for coreference detection of requirement entities based on deep learning and context semantics, to Solve the entity coreference problem in natural language requirements, thereby helping to achieve consensus on entities among multiple stakeholders in different domains

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
  • Demand entity co-reference detection method and device based on deep learning and context semantics
  • Demand entity co-reference detection method and device based on deep learning and context semantics
  • Demand entity co-reference detection method and device based on deep learning and context semantics

Examples

Experimental program
Comparison scheme
Effect test

Embodiment approach

[0077] 1) The above-mentioned embodiments of the present invention are evaluated on short texts, where the context can contain sufficient semantic information. When applied to long text, some context truncated by windows may lack useful information that is too far from entity specific. Resizing the window may alleviate the problem.

[0078] 2) The data of the above embodiments of the present invention come from the financial field. When applied to other domains, around 1000 samples should be labeled in order to fine-tune the entire model for domain adaptation.

[0079] 3) The entities in the data of the present invention are ready-made. To apply the present invention without entities, it is first necessary to extract entities using mature NLP techniques. But errors introduced by these tools inevitably need to be corrected manually.

[0080] 4) When the present invention is applied to other languages, it is necessary to pre-train BERT and word embedding on the corpus of the...

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 a demand entity co-reference detection method and device based on deep learning and context semantics. The method comprises the following steps: 1) context interception: firstly positioning an entity, then intercepting a text according to a window size by taking the entity as a center, and taking a demand text as a context related to the entity; 2) constructing a context similarity network: the network is composed of two parts, one part is a fine tuning BERT model used for learning context representation, and the other part is a Word2Vec-based network used for learningentity representation; respectively inputting the context and the entity into a BERT model and a Word2Vec network, and connecting the two obtained vector representations; and finally, deducing a prediction label by using a multi-layer sensor and a softmax layer, i.e., judging whether the two entities are co-reference entities or not. According to the method, the entity co-reference problem in natural language requirements can be solved, and consensus of entities among stakeholders in multiple different fields is facilitated.

Description

technical field [0001] The invention belongs to the field of computer technology, and relates to requirements engineering, natural language processing and other technologies, especially a coreference resolution technology in natural language processing, which is used to solve the problem of entity coreference in requirements engineering. At the same time, in view of the need to consider contextual semantics and insufficient annotation data in this scenario, a required entity coreference detection scheme based on deep learning and contextual semantics is proposed. This scheme can also be used to solve entity coreference problems in other similar fields. Background technique [0002] Most software requirements are described in natural language, which can be flexibly adapted to arbitrary abstractions. Writing requirements clearly without inconsistencies and ambiguities is a challenging but essential task before entering the later stages of development. Inconsistency is one of ...

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): G06F40/295G06F40/211
CPCG06F40/295G06F40/211
Inventor 王亚文石琳王青
Owner INST OF SOFTWARE - CHINESE ACAD OF SCI
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com