A text implication relationship recognition method based on fusion of multi-granularity information

Abstract

The invention provides a text implication relation recognition method that integrates multi-granularity information, and proposes a modeling method that integrates multi-granularity information fusion and interaction between words and words, words and words, and words and sentences. The present invention first uses the convolutional neural network and the Highway network layer in the character vector layer to establish a word vector model based on the character level, and splicing with the GloVe pre-trained word vector; then the sentence modeling layer uses the word vector of the fusion word granularity to use two-way The long short-term memory network is used to model, and then the sentence matching layer is used to interact and match the text pair with the fusion attention mechanism, and finally the category is obtained by integrating the classification layer; after the model is established, the model is trained and tested, and finally the test sample is obtained. Text entailment recognition classification results. This hierarchical combination structure method that integrates multi-granularity information of characters, words, and sentences combines the advantages of shallow feature positioning and deep feature learning in the model, thereby further improving the accuracy of text implication relationship recognition.

Description

technical field [0001] The present invention relates to the field of natural language processing, and more specifically, relates to a method for identifying text implication relations by fusing multi-granularity information. Background technique [0002] Textual entailment recognition research refers to judging the implied relationship (implicative, contradictory, or neutral) between two given texts (premise text and hypothetical text). This is an important task in the field of natural language processing. Traditional research methods mainly rely on the support of feature engineering, external semantic resources and tools, combined with machine learning methods to complete the text entailment classification. This method based on feature classification usually requires more time and computational cost. With the excellent performance of deep neural networks in various tasks of artificial intelligence, the mainstream research work of text entailment recognition is to use deep ...

AI Technical Summary

Problems solved by technology

This method based on feature classification usually requires more time and computational cost

With the excellent performance of deep neural networks in various tasks of artificial intelligence, the mainstream research work of text entailment recognition is to use deep neural networks to model text sequences to complete the representation and matching of sentences. There are some shortcomings: First, the word2vec, GloVe or Str2Matrix used in the sentence representation process all rely on the existing corpus, and more and more new words, low-frequency words or compound words do not appear or rarely appear in the training corpus , and these words are not all included in the pre-training word vector, the large proportion of new word vector missing will affect the training effect of the model

The second is that the vector representation of two sentences in the mainstream method calculates the distance relationship matrix or the method based on text similarity does not have the ability of semantic reasoning

The third is that there is little discussion on the interactive information between the premise text and the hypothetical text. The existing technology is to encode or map the two texts separately, then simply aggregate the vectors, and then go through the deep sequence model and predict the classification. This process ignores the interaction information between sentences, etc.

Images