Unlock instant, AI-driven research and patent intelligence for your innovation.

Natural language task generation method based on pointer network

A natural language and network technology, applied in special data processing applications, instruments, unstructured text data retrieval, etc., can solve problems such as blunt responses, inability to deal with unregistered words, and weak contextual relevance

Pending Publication Date: 2021-11-26
GUANGDONG ELECTRIC POWER COMM CO LTD
View PDF4 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, the template-based NLG method mainly needs to define a bunch of templates and rules, which has poor flexibility, and the context correlation is not strong, and the reply is blunt
However, many deep learning methods such as the seq2seq model have two shortcomings: first, they cannot accurately reproduce text details, and cannot deal with the problem of unregistered words; second, they tend to generate repeated sentences

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
  • Natural language task generation method based on pointer network
  • Natural language task generation method based on pointer network
  • Natural language task generation method based on pointer network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided for more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0032] The terms "comprising" and "having" and any variations thereof in the description, embodiments, claims and drawings of the present invention are intended to cover non-exclusive inclusion, for example, including a series of steps or units.

[0033] The technical solutions of the present invention will be described in further detail below in conjunction with the accompanying drawings and embodiments.

[0034] Such as figure 1...

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 provides a natural language task generation method based on a pointer network, which is applied to task type man-machine dialogue business, and comprises the following steps: in a man-machine dialogue process, encoding a whole dialogue historical text of a user and a robot to obtain an encoded text; carrying out probability distribution statistics on the coded text by adopting a pointer network to obtain a reply text; and correcting the reply text to obtain a corrected text. The reply text generated by using the pointer network reserves the unregistered words outside the word list, meanwhile, the problem that the text is continuously repeated is avoided, contexts are fused, and the robot keeps a communication mode consistent with the user, so that the dialogue process is clearer and smoother.

Description

technical field [0001] The invention relates to the field of dialog systems, in particular to a pointer network-based natural language task generation method. Background technique [0002] With the development of big data and deep learning technology, the application of man-machine dialogue system in the industry has become more and more extensive. According to the functional division, the dialogue system is divided into three types: knowledge base question answering type, chatting type and task type. Task-based dialogue system is an important branch of human-computer dialogue system, which includes four key components, namely natural language understanding, dialogue state tracking, dialogue policy learning and natural language generation. [0003] The main focus of natural language generation is to express semantic information in the form of human-readable natural language, select and execute certain grammatical and semantic rules to generate natural language text. In the...

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 Applications(China)
IPC IPC(8): G06F16/332G06F16/33G06F16/338G06N20/00
CPCG06F16/3329G06F16/3344G06F16/338G06N20/00
Inventor 周昉昉赖蔚蔚林嘉鑫洪雨天叶杭郑颖龙陈颖璇冯志鹏吴穹
Owner GUANGDONG ELECTRIC POWER COMM CO LTD