A Unified Probabilistic Approach to Referring Expressions

no code implementations • WS 2012 • Kotaro Funakoshi, Mikio Nakano, Takenobu Tokunaga, Ryu Iida

Task-Oriented Dialogue Systems Text Generation

Generating More Specific Questions for Acquiring Attributes of Unknown Concepts from Users

no code implementations • WS 2013 • Tsugumi Otsuka, Kazunori Komatani, Satoshi Sato, Mikio Nakano

Speech Recognition Spoken Dialogue Systems

A Robotic Agent in a Virtual Environment that Performs Situated Incremental Understanding of Navigational Utterances

no code implementations • WS 2013 • Takashi Yamauchi, Mikio Nakano, Kotaro Funakoshi

Language Modelling Speech Recognition +1

User Adaptive Restoration for Incorrectly-Segmented Utterances in Spoken Dialogue Systems

no code implementations • WS 2015 • Kazunori Komatani, Naoki Hotta, Satoshi Sato, Mikio Nakano

Action Detection Speech Recognition +1

Small Talk Improves User Impressions of Interview Dialogue Systems

no code implementations • WS 2016 • Takahiro Kobori, Mikio Nakano, Tomoaki Nakamura

Dialogue Management

Nonparametric Bayesian Models for Spoken Language Understanding

no code implementations • EMNLP 2016 • Kei Wakabayashi, Johane Takeuchi, Kotaro Funakoshi, Mikio Nakano

Slot Filling Spoken Language Understanding

Lexical Acquisition through Implicit Confirmations over Multiple Dialogues

no code implementations • WS 2017 • Kohei Ono, Ryu Takeda, Eric Nichols, Mikio Nakano, Kazunori Komatani

We address the problem of acquiring the ontological categories of unknown terms through implicit confirmation in dialogues.

Chatbot Task-Oriented Dialogue Systems

Collection of Multimodal Dialog Data and Analysis of the Result of Annotation of Users' Interest Level

no code implementations • LREC 2018 • Masahiro Araki, Sayaka Tomimasu, Mikio Nakano, Kazunori Komatani, Shogo Okada, Shinya Fujie, Hiroaki Sugiyama

A Framework for Building Closed-Domain Chat Dialogue Systems

no code implementations • 30 Oct 2019 • Mikio Nakano, Kazunori Komatani

Being able to engage in chat dialogues has been found effective for improving communication between humans and dialogue systems.

Dialogue Management Management +1

User Impressions of Questions to Acquire Lexical Knowledge

no code implementations • SIGDIAL (ACL) 2020 • Kazunori Komatani, Mikio Nakano

We also found that consecutive explicit questions are more annoying than implicit ones when the content of the questions is correct.