Nippon Telegraph and Telephone Corporation

Yasuhito Osugi

Junji Tomita

Kyosuke Nishida

Hisako Asano

Itsumi Saito

A dialogue processing apparatus includes one or more computers each including a memory and a processor configured to receive a question Qas a word string representing a current question in an interactive machine reading comprehension task, a question history {Q, . . . , Q} as a set of word strings representing previous questions, and an answer history {A, . . . , A} as a set of word strings representing previous answers to the previous questions, and use a pre-learned first model parameter, to generate an encoded context vector reflecting an attribute or an importance degree of each of the previous questions and the previous answers; and receive a document P to be used to generate an answer Ato the question Qand the encoded context vector, and use a pre-learned second model parameter, to perform matching between the document and the previous questions and previous answers, to generate the answer.

Dialogue processing apparatus, learning apparatus, dialogue processing method, learning method and program

A generation unit that takes a question Qthat is a word sequence representing a current question in a dialogue, a document P used to generate an answer Ato the question Q, a question history {Q, . . . , Q} that is a set of word sequences representing k past questions, and an answer history {A, . . . , A} that is a set of word sequences representing answers to the k questions as inputs, and generates the answer Aby machine reading comprehension in an extractive mode or a generative mode using pre-trained model parameters is provided.

Growing community of inventors

Tokyo, Japan

Yasuhito Osugi