Chat-crowd: A Dialog-based Platform for Visual Layout Composition
원문 초록
In this paper we introduce Chat-crowd, an interactive environment for visual layout composition via conversational interactions. Chat-crowd supports multiple agents with two conversational roles: agents who play the role of a designer are in charge of placing objects in an editable canvas according to instructions or commands issued by agents with a director role. The system can be integrated with crowdsourcing platforms for both synchronous and asynchronous data collection and is equipped with comprehensive quality controls on the performance of both types of agents. We expect that this system will be useful to build multimodal goal-oriented dialog tasks that require spatial and geometric reasoning.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Exploring the Limits of Natural Language Inference Based Setup for Few-Shot Intent Detection
On the Robustness of Intent Classification and Slot Labeling in Goal-oriented Dialog Systems to Real-world Noise
Benchmarking Commercial Intent Detection Services with Practice-Driven Evaluations
Discriminative Nearest Neighbor Few-Shot Intent Detection by Transferring Natural Language Inference
Effects of Naturalistic Variation in Goal-Oriented Dialog
End-to-End Slot Alignment and Recognition for Cross-Lingual NLU
토론
이 논문과 연결된 포럼 글이 아직 없습니다.