Sentence similarity assessment method based on deep semantic model and semantic role labeling

Abstract

The invention relates to a sentence similarity assessment method based on a deep semantic model and semantic role labeling. The method comprises the steps that a text character string is mapped to a feature vector in the low semantic space, and the cosine similarity is used for measuring the similarity between two sentences; an existing semantic role is reserved, and other semantic roles are processed in a unified mode; according to the similarity between predicates, predicate pairing is performed on sentence pairs to obtain predicate matching pairs, and a similar calculated value between semantic roles is further obtained; the multiple semantic roles of each of the multiple predicates of each sentence are subjected to semantic collocation, the semantic role similarity is calculated, the similarity calculated through the deep semantic model and the similarity calculated on the basis of the semantic roles are linearly combined to be adopted as the final sentence similarity. On the basisof the semantic roles, the Pearson's correlation coefficient is increased by 2.226%, and is 0.226% higher than that of the top one result on the SemEval2017 evaluation official website.

Description

technical field [0001] The invention relates to a natural language processing technology, in particular to a sentence similarity evaluation method based on a deep semantic model and semantic role labeling. Background technique [0002] Sentence Similarity Computing is to measure the semantic equivalence between two sentences, and it is a very important and basic research work in the field of natural language processing. For example, in case-based machine translation, similar sentences are matched by sentence similarity calculation as a candidate set for translation, in automatic question answering systems, the matching of questions and answers, in information filtering, used to eliminate possible spam information, in automatic summarization In the abstract sentences are extracted by similarity, in classification or clustering, it is used to determine the category of sentences or documents, etc. [0003] At present, the similarity research methods of sentences include the me...

AI Technical Summary

Problems solved by technology

[0006] Aiming at the disadvantages that the similarity calculation of sentences based on semantic role labeling in the prior art is based on the similarity of the framework centered on verbs, and cannot make full use of verbs and their dominated component information, the present invention proposes a deep semantic model based on The method for calculating the similarity of sentences marked with semantic roles is analyzed from the sentence structure and semantic level of sentences

Images