Electronics and Telecommunications Research Institute

Jin Seong

Ki Young Lee

Young Kil Kim

Jeong Mu Heo

Young-Ae Seo

Jong Hun Shin

Soojong Lim

Jihee Ryu

Provided is a method of generating a language model using crossmodal information. The method includes: receiving language-based first modality information and non-language-based second modality information; converting the first modality information into a first byte sequence; converting the second modality information into a second byte sequence; converting the first and second byte sequences into a first embedding vector and a second embedding vector by applying an embedding technique for each modality; generating semantic association information between first and second modality information by inputting the first and second embedding vectors to a crossmodal transformer; and learning the language model by setting the generated semantic association information as training data.

Method and apparatus for generating language model using crossmodal information

Growing community of inventors

Daejeon, South Korea

Jin Seong