Dialogue emotion recognition network model system, construction method, equipment and storage medium based on dual knowledge interaction and multi-task learning
A multi-task learning and network model technology, applied in the field of natural language processing, can solve the problems of ignoring the direct interaction between discourse and knowledge, weak auxiliary tasks, etc.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0086] The first embodiment of the present application provides a dialogue emotion recognition network model system based on dual knowledge interaction and multi-task learning (see figure 1 ), including: a task definition module, which is used for a set of dialogues in a given dialogue dataset to predict the emotional label of each target utterance given the dialogue history information; an encoder, which uses the XLNet encoder to model the dialogue history information; knowledge integration module, used for common sense knowledge extraction, and knowledge enhancement representation based on graph attention network; self-matching module, used for the interaction between discourse and knowledge; dialogue emotion recognition module, combined with dialogue history information to predict the current target discourse The sentiment labels of ; the sentiment polarity intensity prediction task module, which is used to introduce knowledge strongly related to the main task into the model...
Embodiment 2
[0088] The second embodiment of the present application provides a method for constructing a dialogue emotion recognition network model based on dual knowledge interaction and multi-task learning (see figure 2 ), the method is specifically:
[0089] Step 1: Given a set of dialogues in the dialogue dataset, predict the emotional label of each target utterance given the historical information of the dialogue;
[0090] The dialogue emotion recognition task is defined as follows: given where i=1,...,N,j=1,...,N i , representing a collection of dialogue pairs {utterances, labels} in the dialogue dataset. Conversation X contains N utterances, each utterance X i contains N i words, expressed as every X i by p(X i ) ∈ P, where P is the set of speakers. discrete value Y i ∈S is used to denote sentiment labels, where S denotes the set of sentiment labels, and |S|=h c . The goal of the dialogue emotion recognition task is to predict each target utterance X given the dialogu...
Embodiment 3
[0143] The third embodiment of the present application provides an electronic device, see image 3 , the electronic device takes the form of a general-purpose computing device. Components of an electronic device may include, but are not limited to, one or more processors or processing units, memory for storing a computer program capable of running on the processors, interfacing with various system components (including memory, one or more processors or processing unit) bus.
[0144] Wherein, when the one or more processors or processing units are configured to run the computer program, the steps of the method described in Embodiment 2 are executed. The types of processors used include central processing units, general purpose processors, digital signal processors, application specific integrated circuits, field programmable gate arrays or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof.
[0145] The bus represents o...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More