Method and apparatus with natural language generation
AssigneeSamsung Electronics Co., Ltd.
InventorsJehun JEON, Young-Seok KIM, Sang Hyun YOO, Junhwi CHOI
Life of this patent
Estimating the term…
Abstract
Provided is a processor-implemented method of generating a natural language, the method including generating a latent variable from an embedding vector that corresponds to an input utterance, determining attention information related to the input utterance by applying the generated latent variable to a neural network model, and outputting a natural language response that corresponds to the input utterance based on the calculated attention information.
Claims19
A processor-implemented method of generating a natural language, the method comprising:
- generating a latent variable from an embedding vector that corresponds to an input utterance;
- determining attention information related to the input utterance by applying the generated latent variable to a neural network model;
- and
- outputting a natural language response that corresponds to the input utterance based on the calculated attention information.
An apparatus for generating a natural language, the apparatus comprising:
- a processor configured to:
- generate a latent variable from an embedding vector that corresponds to an input utterance;
- determine attention information related to the input utterance by applying the generated latent variable to a neural network model, and
- output a natural language response that corresponds to the input utterance based on the calculated attention information.
A processor-implemented method of generating a natural language, the method comprising:
- generating a sentence-level latent variable from a first embedding vector that corresponds to a complete input utterance;
- generating a word-level latent variable based on a second embedding vector of each word included in the input utterance and the sentence-level latent variable;
- determining attention information related to the input utterance by applying the generated word-level latent variable to an attention model;
- and
- outputting a natural language response that corresponds to the input utterance based on the calculated attention information.
An apparatus for generating a natural language, the apparatus comprising:
- a processor configured to:
- generate a sentence-level latent variable from a first embedding vector corresponding to a complete input utterance;
- generate a word-level latent variable based on a second embedding vector of each word in the input utterance and the sentence-level latent variable;
- determine attention information related to the input utterance by applying the generated word-level latent variable to a neural network model, and output a natural language response that corresponds to the input utterance based on the calculated attention information.
Dependencies are inferred from the claim text.