A Text Implication Recognition Method Based on Deep Learning
A technology of deep learning and relationship recognition, applied in the field of text implication relationship recognition based on deep learning, to achieve the effect of understanding tasks, improving efficiency and accuracy, and better understanding tasks
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0074] In this embodiment, a text implication relationship recognition algorithm based on deep learning is specifically carried out as follows:
[0075] Take two texts, one of which is the "premise" and the other is the "assumption":
[0076] Premise: Two women having drinks and smoking cigarettes at the bar.
[0077] Assumption: Two women are at a bar.
[0078] The default maximum statement length is 15.
[0079] Step 1: Preprocess the "premise" and "assumption" to generate the "premise" string S p = ["Two", "women", "having", "drinks", "and", "smoking", "cigarettes", "at", "the", "bar", "."] and "assumption" String S h =["Two", "women", "are", "at", "a", "bar", "."];
[0080] Step 2: Put the "premise" character S p and the "assumed" string S h , using the Str2Matrix method to generate n×l max The "premise" of the fundamental matrix M p and n×l max The "hypothetical" fundamental matrix M of h ;
[0081] where WV word Represents the n-dimensional word vector of ...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


