DQN-TAMER: Human-in-the-Loop Reinforcement Learning with Intractable Feedback

1 code implementation • 28 Oct 2018 • Riku Arakawa, Sosuke Kobayashi, Yuya Unno, Yuta Tsuboi, Shin-ichi Maeda

A remedy for this is to train an agent with real-time feedback from a human observer who immediately gives rewards for some actions.

reinforcement-learning Reinforcement Learning (RL)

Addressee and Response Selection for Multilingual Conversation

1 code implementation • COLING 2018 • Motoki Sato, Hiroki Ouch, Yuta Tsuboi

In this task, a conversational system predicts an appropriate addressee and response for an input message in multiple languages.

Transfer Learning

Interactively Picking Real-World Objects with Unconstrained Spoken Language Instructions

1 code implementation • 17 Oct 2017 • Jun Hatori, Yuta Kikuchi, Sosuke Kobayashi, Kuniyuki Takahashi, Yuta Tsuboi, Yuya Unno, Wilson Ko, Jethro Tan

In this paper, we propose the first comprehensive system that can handle unconstrained spoken language and is able to effectively resolve ambiguity in spoken instructions.

object-detection Object Detection

Addressee and Response Selection for Multi-Party Conversation

1 code implementation • EMNLP 2016 • Hiroki Ouchi, Yuta Tsuboi

Short-Text Conversation

Neural Networks Leverage Corpus-wide Information for Part-of-speech Tagging

no code implementations • EMNLP 2014 • Yuta Tsuboi

Feature Engineering Part-Of-Speech Tagging +1

Learning from a Neighbor: Adapting a Japanese Parser for Korean Through Feature Transfer Learning

no code implementations • WS 2014 • Hiroshi Kanayama, Youngja Park, Yuta Tsuboi, Dongmook Yi

Cross-Lingual Transfer Dependency Parsing +4