Related papers: Multimodal Dialog Systems with Dual Knowledge-enha…
Dialogue generation has been successfully learned from scratch by neural networks, but tends to produce the same general response, e.g., "what are you talking about?", in many conversations. To reduce this homogeneity, external knowledge…
This paper describes our submission for the End-to-end Multi-domain Task Completion Dialog shared task at the 9th Dialog System Technology Challenge (DSTC-9). Participants in the shared task build an end-to-end task completion dialog system…
Extending pre-trained text Large Language Models (LLMs)'s speech understanding or generation abilities by introducing various effective speech tokens has attracted great attention in the speech community. However, building a unified speech…
Task-oriented conversational modeling with unstructured knowledge access, as track 1 of the 9th Dialogue System Technology Challenges (DSTC 9), requests to build a system to generate response given dialogue history and knowledge access.…
The goal of text generation is to make machines express in human language. It is one of the most important yet challenging tasks in natural language processing (NLP). Since 2014, various neural encoder-decoder models pioneered by Seq2Seq…
Building robust and general dialogue models for spoken conversations is challenging due to the gap in distributions of spoken and written data. This paper presents our approach to build generalized models for the Knowledge-grounded…
The knowledge-grounded dialogue task aims to generate responses that convey information from given knowledge documents. However, it is a challenge for the current sequence-based model to acquire knowledge from complex documents and…
Document Grounded Conversations is a task to generate dialogue responses when chatting about the content of a given document. Obviously, document knowledge plays a critical role in Document Grounded Conversations, while existing dialogue…
In recent times, Vision-Language Models (VLMs) have been trained under two predominant paradigms. Generative training has enabled Multimodal Large Language Models (MLLMs) to tackle various complex tasks, yet issues such as hallucinations…
Existing studies in dialogue system research mostly treat task-oriented dialogue and chit-chat as separate domains. Towards building a human-like assistant that can converse naturally and seamlessly with users, it is important to build a…
Semantic communication is emerging as a promising paradigm that focuses on the extraction and transmission of semantic meanings using deep learning techniques. While current research primarily addresses the reduction of semantic…
This paper presents an ontology-aware pretrained language model (OPAL) for end-to-end task-oriented dialogue (TOD). Unlike chit-chat dialogue models, task-oriented dialogue models fulfill at least two task-specific modules: dialogue state…
Target-guided response generation enables dialogue systems to smoothly transition a conversation from a dialogue context toward a target sentence. Such control is useful for designing dialogue systems that direct a conversation toward…
Collection of annotated dialogs for training task-oriented dialog systems have been one of the key bottlenecks in improving current models. While dialog response generation has been widely studied on the agent side, it is not evident if…
How to incorporate external knowledge into a neural dialogue model is critically important for dialogue systems to behave like real humans. To handle this problem, memory networks are usually a great choice and a promising way. However,…
Current Knowledge-Grounded Dialogue Generation (KDG) models specialize in producing rational and factual responses. However, to establish long-term relationships with users, the KDG model needs the capability to generate responses in a…
Achieving seamless, human-like interaction remains a key challenge for full-duplex spoken dialogue models (SDMs). Reinforcement learning (RL) has substantially enhanced text- and vision-language models, while well-designed reward signals…
In recent years, 3D models have been utilized in many applications, such as auto-driver, 3D reconstruction, VR, and AR. However, the scarcity of 3D model data does not meet its practical demands. Thus, generating high-quality 3D models…
End-to-end neural models for intelligent dialogue systems suffer from the problem of generating uninformative responses. Various methods were proposed to generate more informative responses by leveraging external knowledge. However, few…
Current general-purpose large language models (LLMs) commonly exhibit knowledge hallucination and insufficient domain-specific adaptability in domain-specific tasks, limiting their effectiveness in specialized question answering scenarios.…