Chat, Shift and Perform: Bridging the Gap between Task-oriented and Non-task-oriented Dialog Systems

no code implementations • 5 Jun 2022 • Teppei Yoshino, Yosuke Fukuchi, Shoya Matsumori, Michita Imai

We propose CASPER (ChAt, Shift and PERform), a novel dialog system consisting of three types of dialog models: chatter, shifter, and performer.

LatteGAN: Visually Guided Language Attention for Multi-Turn Text-Conditioned Image Manipulation

1 code implementation • 28 Dec 2021 • Shoya Matsumori, Yuki Abe, Kosuke Shingyouchi, Komei Sugiura, Michita Imai

Previous models for this task successfully generate images iteratively, given a sequence of instructions and a previously generated image.

Image Manipulation Text-to-Image Generation

Unified Questioner Transformer for Descriptive Question Generation in Goal-Oriented Visual Dialogue

1 code implementation • ICCV 2021 • Shoya Matsumori, Kosuke Shingyouchi, Yuki Abe, Yosuke Fukuchi, Komei Sugiura, Michita Imai

In addition, we build a goal-oriented visual dialogue task called CLEVR Ask.

Descriptive Question Generation +1

SLAM-Inspired Simultaneous Contextualization and Interpreting for Incremental Conversation Sentences

no code implementations • 29 May 2020 • Yusuke Takimoto, Yosuke Fukuchi, Shoya Matsumori, Michita Imai

In many methods, however, only one meaning is considered for one label of a word, and multiple meanings of polysemous words depending on the context are rarely handled.

Simultaneous Localization and Mapping