Neural network natural language inference method combining single word semantic knowledge

Abstract

The invention discloses a neural network natural language inference method combining single word semantic knowledge. The method comprises the steps of extracting various semantic relations between word pairs from an external semantic knowledge base; constructing a neural network model, utilizing the neural network model to conduct local inference modeling on input prerequisite text, hypothetical text and the semantic relations between the word pairs, combining local inference information to obtain inference information at a sentence level, and training the neural network model at last; inputting the unlabeled prerequisite text and hypothetical text into the trained neural network model, calculating and obtaining probability distributions belonging to three categories, and selecting the category corresponding to the maximum probability as a final prediction category. The method improves the accuracy of natural language inference and solves the problem that external semantic knowledge isless utilized in traditional neural network schemes.

Description

technical field [0001] The invention relates to the field of natural language processing, in particular to a neural network natural language reasoning method which integrates word semantic knowledge. Background technique [0002] Natural Language Inference (NLI), also known as Recognizing Textual Entailment (RTE), refers to judging whether a natural language premise text (Premise, P) can infer a natural language hypothetical text (Hypothesis, H). This concept was first proposed by Dagan et al. in 2004. The usual task is to do three classifications, 1) the premise contains assumptions, 2) the two are contradictory, and 3) the two are neutral. [0003] for example: [0004] Premise: Liu Qingfeng founded HKUST Xunfei Co., Ltd. in 1999. [0005] Hypothesis 1: Liu Qingfeng is the founder of HKUST Xunfei. [0006] Hypothesis 2: Liu Qingfeng is not the founder of HKUST Xunfei. [0007] Hypothesis 3: Liu Qingfeng graduated from HKUST. [0008] Obviously, the relationship betwe...

AI Technical Summary

Problems solved by technology

[0012] The methods described above are usually based on artificially constructed complex features, so their robustness and scalability are limited

Images