Search Results for author: Nobuhiro Kaji

Found 14 papers, 1 papers with code

Conversation Initiation by Diverse News Contents Introduction

no code implementations NAACL 2019 Satoshi Akasaki, Nobuhiro Kaji

In this paper, we consider the system as a conversation initiator and propose a novel task of generating the initial utterance in open-domain non-task-oriented conversation.

Information Retrieval Retrieval

Predicting Causes of Reformulation in Intelligent Assistants

no code implementations WS 2017 Shumpei Sano, Nobuhiro Kaji, Manabu Sassano

To remove this hindrance, we focus on reformulation, which is a useful signal of user dissatisfaction, and propose a method to predict the reformulation causes.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +3

Chat Detection in an Intelligent Assistant: Combining Task-oriented and Non-task-oriented Spoken Dialogue Systems

no code implementations ACL 2017 Satoshi Akasaki, Nobuhiro Kaji

Recently emerged intelligent assistants on smartphones and home electronics (e. g., Siri and Alexa) can be seen as novel hybrids of domain-specific task-oriented spoken dialogue systems and open-domain non-task-oriented ones.

Spoken Dialogue Systems

Incremental Skip-gram Model with Negative Sampling

1 code implementation EMNLP 2017 Nobuhiro Kaji, Hayato Kobayashi

This paper explores an incremental training strategy for the skip-gram model with negative sampling (SGNS) from both empirical and theoretical perspectives.

Word Embeddings

Cannot find the paper you are looking for? You can Submit a new open access paper.