A Fact Detection-Oriented Evidence and Claim Joint Extraction Method
A technology of evidence and statement, applied in the field of joint extraction of evidence and statement for fact detection, can solve problems such as inability to accurately find evidence, and achieve the effect of improved understanding
Active Publication Date: 2022-07-29
SUN YAT SEN UNIV
View PDF4 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0007] In order to overcome the defect that the evidence cannot be accurately searched in the fact detection process described in the prior art, the present invention provides a method for joint extraction of evidence and statements oriented to fact detection
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0071] This embodiment provides a method for jointly extracting evidence and statement for fact detection, the method includes the following steps:
[0072] The method includes the following steps:
[0073] S1: Specify the expected database for retrieval and a statement to be verified, clean the corpus, and perform entity extraction on the statement to obtain an entity set;
[0074] S2: Document retrieval: For the statement to be verified, use the entity linking method to retrieve and construct the corresponding candidate document set from the cleaned corpus according to the entity set, and use all sentences in the set as the candidate sentence set;
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
Login to View More Abstract
The present invention relates to a method for joint extraction of evidence and statement oriented to fact detection, comprising: S1: designate an expected database for retrieval and a statement to be verified, clean the corpus, and perform entity extraction on the statement to obtain an entity set; S2: Document retrieval: For a given statement, use the entity linking method to retrieve and construct the corresponding candidate document set from the cleaned corpus according to the entity set, and use all sentences in the set as the candidate sentence set; S3: based on greedy strategy The evidence search method is used to construct evidence, and use the pre-trained language model BERT as the evaluation model of the evidence to train and test the evaluation model to obtain the final target evidence and category. The present invention can effectively improve the accuracy of evidence search.
Description
technical field [0001] The present invention relates to the field of automatic fact detection, and more particularly, to a method for joint extraction of evidence and statement oriented to fact detection. Background technique [0002] The purpose of automatic fact detection is to enable computers to automatically identify and filter false information on the Internet, so as to ensure the authenticity and reliability of information. With the successful application of deep learning in natural language processing in recent years, more and more research efforts have attempted to incorporate deep learning techniques into automatic fact-checking work and achieved good results. The fact detection task is a kind of automatic fact detection task, which is used to determine the authenticity of a given statement, which involves two goals: (1) Evidence mining, that is, for a given statement, retrieved from Wikipedia The sentence set with the highest correlation with the statement is use...
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06F16/215G06F16/2458G06F16/23G06F16/28G06F40/30
CPCG06F16/215G06F16/2465G06F16/23G06F16/285G06F40/30
Inventor 万海陈海城黄佳莉曾娟赵杭
Owner SUN YAT SEN UNIV