Architecture for generating QA pairs from contexts
The present invention relates to a context-based QA generation architecture, and an object of the present invention is to generate diverse QA pairs from a single context. To achieve the object, the present invention includes a latent variable generating network including at least one encoder and an artificial neural network (Multi-Layer Perceptron: MLP) and configured to train the artificial neural network using a first context, a first question, and a first answer, and generate a second question latent variable and a second answer latent variable by applying the trained artificial neural network to a second context, an answer generating network configured to generate a second answer by decoding the second answer latent variable, and a question generating network configured to generate a second question based on a second context and the second answer.
1. A context-based QA generating device, comprising:
a latent variable generating network including at least one encoder and an artificial neural network (Multi-Layer Perceptron: MLP) and configured to train the artificial neural network using a first context, a first question, and a first answer, and generate a second question latent variable and a second answer latent variable by applying the trained artificial neural network to a second context;
an answer generating network configured to generate a second answer by decoding the second answer latent variable; and
a question generating network configured to generate a second question based on the second context and the second answer;
wherein the second question and the second answer are characterized by a high mutual information to strengthen a consistency; and wherein the second answer latent variable is forced to be dependent on the second question latent variable.
2. The context-based QA generating device of claim 1 , wherein the latent variable generating network is configured to:
encode the first context and the first question to generate a first context vector and a first question vector, respectively,
generate a first question latent variable based on the first context vector and the first question vector, and
generate a first answer latent variable based on the first question latent variable and the first answer vector.
3. The context-based QA generating device of claim 2 , wherein the context-based QA generating device trains the artificial neural network based on the first context, the first question latent variable, and the first answer latent variable.
4. The context-based QA generating device of claim 2 , wherein the first question latent variable and the first answer latent variable include constraints according to distribution.
5. The context-based QA generating device of claim 1 , wherein the answer generating network is configured to generate a second answer by predicting a start and end points of a correct answer span based on context information of the second context and the second answer latent variable.
6. The context-based QA generating device of claim 1 , wherein the question generating network is configured to generate a third context vector and a third answer vector by further encoding the second context and the second answer, and generate a second question based on the third context vector and the third answer vector.
7. The context-based QA generating device of claim 6 , wherein an attention mechanism is used to minimize loss occurring in decoding of the third context vector and the third answer vector.
8. The context-based QA generating device of claim 1 , wherein the context-based QA generating device comprises a hierarchical conditional variational autoencoder.
9. The context-based QA generating device of claim 8 , wherein the hierarchical conditional variational autoencoder is configured to provide a neural estimation value to maximize the mutual information between the second question and the second answer.
10. The context-based QA generating device of claim 8 , wherein the hierarchical conditional variational autoencoder is configured to separate the answer generating network and the question generating network to allow for unlimited questions being generated from a single context.
11. The context-based QA generating device of claim 1 , a reverse dependency is obtained by sampling the second question.
12. The context-based QA generating device of claim 1 , wherein the second context is received from a user, the second context comprises m tokens, and the second question comprises n tokens based on the second context, and the second answer comprises 1 token based on the second context.