A method for natural language inference based on conjunction tagging and reinforcement learning

A natural language and reinforcement learning technology, applied in inference methods, neural learning methods, semantic analysis, etc., can solve problems such as the inability to achieve good results with large-scale data sets, and achieve the effect of improving accuracy

Active Publication Date: 2021-09-21
ZHEJIANG UNIV
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This approach is too simple to achieve good results on large-scale datasets

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
  • A method for natural language inference based on conjunction tagging and reinforcement learning
  • A method for natural language inference based on conjunction tagging and reinforcement learning
  • A method for natural language inference based on conjunction tagging and reinforcement learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0043] The specific embodiments of the present invention will be described below with reference to the accompanying drawings, so that those skilled in the art can better understand the present invention.

[0044] like figure 1 As shown, a natural language inference method based on conjunction tagging and reinforcement learning includes the following steps:

[0045] S01, train a simple conjunction prediction model on the conjunction prediction task. We use BookCorpus, a large-scale comprehensive corpus, as the training set, and the preprocessed dataset is in the form of (sentence 1, sentence 2, conjunction markers). Our task is to, given sentence 1 and sentence 2, predict the conjunctions that were originally used in the corpus to connect them. like figure 2 As shown, when performing the task of conjunction prediction, we use the existing word vector Glove to make word embeddings for sentences, and then send them into a bidirectional long-term memory network (encoder). We ...

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 present invention provides a natural language inference method based on conjunction marking and reinforcement learning, comprising the following steps: (1) training a conjunction prediction model on the conjunction prediction task; (2) inputting premise and conjecture in the natural language inference model Encode the text and use the encoder to obtain the expression matrix; (3) Embed the encoder of the conjunction prediction model into the natural language reasoning model, and send the premise and guessed word vector obtained in the encoding process of step (2) to the pre-set The trained encoder and output the expression vector; (4) interact the encoder of the natural language inference model with the encoder of the embedded conjunction prediction model in the attention mechanism to obtain an attention vector; (5) combine the attention Convert the vector to a probability distribution and output the result. By using the present invention, the accuracy rate of natural language reasoning tasks on large-scale data sets is greatly improved by transferring the knowledge learned from other supervised learning tasks.

Description

technical field [0001] The invention relates to the field of natural language processing, in particular to a natural language reasoning method based on conjunction marking and reinforcement learning. Background technique [0002] Natural language inference has always been one of the hottest and toughest problems in natural language processing. In the most popular tasks at present, given two sentences (premise sentence, conjecture sentence), we need to judge whether the logical relationship between the two sentences is entailment, neutrality or contradiction. An efficient natural language inference model can be widely used in many fields based on semantic understanding, such as dialogue robots, question answering systems and text generation systems. [0003] Early natural language reasoning tasks are based on small datasets, and the methods used are also traditional methods such as natural logic method and shadow method. Such datasets cannot support complex models with larg...

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
Patent Type & Authority Patents(China)
IPC IPC(8): G06N5/04G06F40/30G06N3/08
CPCG06N3/08G06N5/04G06F40/30
Inventor 潘博远蔡登赵洲何晓飞
Owner ZHEJIANG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap