Related papers: FADO: Feedback-Aware Double COntrolling Network fo…
The task of Image-to-Video (I2V) generation aims to synthesize a video from a reference image and a text prompt. This requires diffusion models to reconcile high-frequency visual constraints and low-frequency textual guidance during the…
Multimodal Emotion Recognition in Conversation (ERC) plays an influential role in the field of human-computer interaction and conversational robotics since it can motivate machines to provide empathetic services. Multimodal data modeling is…
Spoken conversational systems require more than accurate speech generation to have human-like conversations: to feel natural and engaging, they must produce conversational behaviour that adapts dynamically to the context. Current spoken…
Dialogue act annotations are important to improve response generation quality in task-oriented dialogue systems. However, it can be challenging to use dialogue acts to control response generation in a generalizable way because different…
Human conversation is organized by an implicit chain of thoughts that manifests as timed speech acts. Capturing this causal pathway is key to building natural full-duplex interactive systems. We introduce a framework that enables reasoning…
We present a method to control a text-to-image generative model to produce training data useful for supervised learning. Unlike previous works that employ an open-loop approach and pre-define prompts to generate new data using either a…
Recent years have witnessed great progress on building emotional chatbots. Tremendous methods have been proposed for chatbots to generate responses with given emotions. However, the emotion changes of the user during the conversation has…
Transformer-based pre-trained language models boost the performance of open-domain dialogue systems. Prior works leverage Transformer-based pre-trained language models to generate texts with desired attributes in two general approaches: (1)…
Emotional support is a crucial skill for many real-world scenarios, including caring for the elderly, mental health support, and customer service chats. This paper presents a novel task of empathetic dialog generation with positive emotion…
Emotion-controllable response generation is an attractive and valuable task that aims to make open-domain conversations more empathetic and engaging. Existing methods mainly enhance the emotion expression by adding regularization terms to…
Emotion plays a pivotal role in shaping negotiation outcomes, influencing trust, cooperation, and long-term relationships. Developing negotiation dialog systems that can recognize and respond strategically to emotions is, therefore,…
Being able to generate informative and coherent dialogue responses is crucial when designing human-like open-domain dialogue systems. Encoder-decoder-based dialogue models tend to produce generic and dull responses during the decoding step…
Emotion recognition has a wide range of applications in human-computer interaction, marketing, healthcare, and other fields. In recent years, the development of deep learning technology has provided new methods for emotion recognition.…
While affective computing has advanced considerably, multimodal emotion prediction in aging populations remains underexplored, largely due to the scarcity of dedicated datasets. Existing multimodal benchmarks predominantly target young,…
The goal of building intelligent dialogue systems has largely been separately pursued under two paradigms: task-oriented dialogue (TOD) systems, which perform goal-oriented functions, and open-domain dialogue (ODD) systems, which focus on…
We describe a two-step approach for dialogue management in task-oriented spoken dialogue systems. A unified neural network framework is proposed to enable the system to first learn by supervision from a set of dialogue data and then…
Establishing retrieval-based dialogue systems that can select appropriate responses from the pre-built index has gained increasing attention from researchers. For this task, the adoption of pre-trained language models (such as BERT) has led…
Many studies have applied reinforcement learning to train a dialog policy and show great promise these years. One common approach is to employ a user simulator to obtain a large number of simulated user experiences for reinforcement…
The recognition of emotion and dialogue acts enriches conversational analysis and help to build natural dialogue systems. Emotion interpretation makes us understand feelings and dialogue acts reflect the intentions and performative…
Standardized Student Evaluation of Teaching often suffer from low reliability, restricted response options, and response distortion. Existing machine learning methods that mine open-ended comments usually reduce feedback to binary…