Alert button
Picture for Satoshi Nakamura

Satoshi Nakamura

Alert button

Conversational Response Re-ranking Based on Event Causality and Role Factored Tensor Event Embedding

Jun 24, 2019
Shohei Tanaka, Koichiro Yoshino, Katsuhito Sudoh, Satoshi Nakamura

Figure 1 for Conversational Response Re-ranking Based on Event Causality and Role Factored Tensor Event Embedding
Figure 2 for Conversational Response Re-ranking Based on Event Causality and Role Factored Tensor Event Embedding
Figure 3 for Conversational Response Re-ranking Based on Event Causality and Role Factored Tensor Event Embedding
Figure 4 for Conversational Response Re-ranking Based on Event Causality and Role Factored Tensor Event Embedding
Viaarxiv icon

From Speech Chain to Multimodal Chain: Leveraging Cross-modal Data Augmentation for Semi-supervised Learning

Jun 03, 2019
Johanes Effendi, Andros Tjandra, Sakriani Sakti, Satoshi Nakamura

Figure 1 for From Speech Chain to Multimodal Chain: Leveraging Cross-modal Data Augmentation for Semi-supervised Learning
Figure 2 for From Speech Chain to Multimodal Chain: Leveraging Cross-modal Data Augmentation for Semi-supervised Learning
Figure 3 for From Speech Chain to Multimodal Chain: Leveraging Cross-modal Data Augmentation for Semi-supervised Learning
Figure 4 for From Speech Chain to Multimodal Chain: Leveraging Cross-modal Data Augmentation for Semi-supervised Learning
Viaarxiv icon

VQVAE Unsupervised Unit Discovery and Multi-scale Code2Spec Inverter for Zerospeech Challenge 2019

May 29, 2019
Andros Tjandra, Berrak Sisman, Mingyang Zhang, Sakriani Sakti, Haizhou Li, Satoshi Nakamura

Figure 1 for VQVAE Unsupervised Unit Discovery and Multi-scale Code2Spec Inverter for Zerospeech Challenge 2019
Figure 2 for VQVAE Unsupervised Unit Discovery and Multi-scale Code2Spec Inverter for Zerospeech Challenge 2019
Figure 3 for VQVAE Unsupervised Unit Discovery and Multi-scale Code2Spec Inverter for Zerospeech Challenge 2019
Figure 4 for VQVAE Unsupervised Unit Discovery and Multi-scale Code2Spec Inverter for Zerospeech Challenge 2019
Viaarxiv icon

An Incremental Turn-Taking Model For Task-Oriented Dialog Systems

May 28, 2019
Andrei C. Coman, Koichiro Yoshino, Yukitoshi Murase, Satoshi Nakamura, Giuseppe Riccardi

Figure 1 for An Incremental Turn-Taking Model For Task-Oriented Dialog Systems
Figure 2 for An Incremental Turn-Taking Model For Task-Oriented Dialog Systems
Figure 3 for An Incremental Turn-Taking Model For Task-Oriented Dialog Systems
Figure 4 for An Incremental Turn-Taking Model For Task-Oriented Dialog Systems
Viaarxiv icon

Optimization of Information-Seeking Dialogue Strategy for Argumentation-Based Dialogue System

Nov 26, 2018
Hisao Katsumi, Takuya Hiraoka, Koichiro Yoshino, Kazeto Yamamoto, Shota Motoura, Kunihiko Sadamasa, Satoshi Nakamura

Figure 1 for Optimization of Information-Seeking Dialogue Strategy for Argumentation-Based Dialogue System
Figure 2 for Optimization of Information-Seeking Dialogue Strategy for Argumentation-Based Dialogue System
Figure 3 for Optimization of Information-Seeking Dialogue Strategy for Argumentation-Based Dialogue System
Figure 4 for Optimization of Information-Seeking Dialogue Strategy for Argumentation-Based Dialogue System
Viaarxiv icon

Another Diversity-Promoting Objective Function for Neural Dialogue Generation

Nov 21, 2018
Ryo Nakamura, Katsuhito Sudoh, Koichiro Yoshino, Satoshi Nakamura

Figure 1 for Another Diversity-Promoting Objective Function for Neural Dialogue Generation
Figure 2 for Another Diversity-Promoting Objective Function for Neural Dialogue Generation
Figure 3 for Another Diversity-Promoting Objective Function for Neural Dialogue Generation
Figure 4 for Another Diversity-Promoting Objective Function for Neural Dialogue Generation
Viaarxiv icon

End-to-End Feedback Loss in Speech Chain Framework via Straight-Through Estimator

Oct 31, 2018
Andros Tjandra, Sakriani Sakti, Satoshi Nakamura

Figure 1 for End-to-End Feedback Loss in Speech Chain Framework via Straight-Through Estimator
Figure 2 for End-to-End Feedback Loss in Speech Chain Framework via Straight-Through Estimator
Figure 3 for End-to-End Feedback Loss in Speech Chain Framework via Straight-Through Estimator
Figure 4 for End-to-End Feedback Loss in Speech Chain Framework via Straight-Through Estimator
Viaarxiv icon

Multi-Source Neural Machine Translation with Data Augmentation

Oct 16, 2018
Yuta Nishimura, Katsuhito Sudoh, Graham Neubig, Satoshi Nakamura

Figure 1 for Multi-Source Neural Machine Translation with Data Augmentation
Figure 2 for Multi-Source Neural Machine Translation with Data Augmentation
Figure 3 for Multi-Source Neural Machine Translation with Data Augmentation
Figure 4 for Multi-Source Neural Machine Translation with Data Augmentation
Viaarxiv icon

Training Neural Machine Translation using Word Embedding-based Loss

Jul 30, 2018
Katsuki Chousa, Katsuhito Sudoh, Satoshi Nakamura

Figure 1 for Training Neural Machine Translation using Word Embedding-based Loss
Figure 2 for Training Neural Machine Translation using Word Embedding-based Loss
Figure 3 for Training Neural Machine Translation using Word Embedding-based Loss
Figure 4 for Training Neural Machine Translation using Word Embedding-based Loss
Viaarxiv icon