Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Question and answering (QA) system realization method based on deep learning and topic model

A topic model and implementation method technology, applied in neural learning methods, biological neural network models, special data processing applications, etc., can solve problems such as inability to create new answer content, generation content dependence, poor transferability, etc.

Active Publication Date: 2018-11-06
SOUTH CHINA UNIV OF TECH
View PDF4 Cites 66 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The first is the template matching model. We can design rules to let the dialogue model know that when it encounters questions in different languages, it will reply with different content. This method needs to design multiple rules and consider the order of priority among the rules. The better the content of the answer, but the model is less transferable
2. In addition, the retrieval model is similar to a search engine. The difference is that the retrieval model gives us answers. This model mainly matches question-answer pairs, depending on the similarity between the input question sentence and the answer candidate set, but generates The content depends on the data set and cannot create new answer content

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
  • Question and answering (QA) system realization method based on deep learning and topic model
  • Question and answering (QA) system realization method based on deep learning and topic model
  • Question and answering (QA) system realization method based on deep learning and topic model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0050] The present invention will be further described below in conjunction with specific examples.

[0051] Such as figure 1 As shown, a method for implementing a question answering system based on deep learning and topic models provided in this embodiment includes the following steps:

[0052] Step S1. First, input the question sentence into the Twitter LDA topic model to obtain the topic type of the question sentence, and extract the corresponding topic words, and represent the input question sentence and the topic words as word vectors. The specific process is as follows:

[0053] First, the topic words are extracted by the Twitter LDA topic model. First, the question and answer need to be composed of a question-answer pair {post, answer}. At this time, the question-answer pair is a short text that meets the requirements of the Twitter LDA topic model. The topic model assumes that each {post, answer} It is classified into a certain topic, and the words in the original que...

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 invention discloses a question and answering (QA) system realization method based on deep learning and a topic model. The method comprises the steps of: S1, inputting a question sentence to the Twitter LDA topic model to obtain a topic type of the question sentence, extracting a corresponding topic word, and indicating the input question sentence and the topic word as word vectors; S2, inputting word vectors of the input question sentence to a recurrent neural network (RNN) for encoding to obtain an encoded hidden-layer state vector of the question sentence; S3, using a joint attention mechanism and combining local and global hybrid semantic vectors of the question sentence by a decoding recurrent neural network for decoding to generate words; S4, using a large-scale conversation corpus to train a deep-learning topic question and answering model based on an encoding-decoding framework; and S5, using the trained question and answering model to predict an answer to the input questionsentence, and generating answers related to a question sentence topic. The method makes up for the lack of exogenous knowledge of question and answering models, and increases richness and diversity of answers.

Description

technical field [0001] The present invention relates to the technical field of question answering systems in natural language processing, in particular to a question answering system implementation method based on deep learning and topic models. Background technique [0002] Human-machine dialogue is a challenging task in Natural Language Processing (NLP) and real artificial intelligence. Existing question and answering (QA) systems include task-specific question answering systems and open domain question answering system. The question answering system is designed to help humans complete specific tasks, such as completing instructions issued by people and guiding people to complete a certain task. At the same time, the question answering system is designed to complete the process of imitating natural human chatting in different chat contexts. A lot of research has focused on dialogue systems before. With the explosive growth of social media data on the Internet, a large amo...

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
IPC IPC(8): G06F17/30G06F17/27G06N3/04G06N3/08
CPCG06N3/08G06F40/30G06N3/044
Inventor 詹国辉俞祝良
Owner SOUTH CHINA UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products