Related papers: Taskmaster-1: Toward a Realistic and Diverse Dialo…
In order to better simulate the real human conversation process, models need to generate dialogue utterances based on not only preceding textual contexts but also visual contexts. However, with the development of multi-modal dialogue…
The recent paradigm shift toward large reasoning models (LRMs) as autonomous agents has intensified the demand for sophisticated, multi-turn tool-use capabilities. Yet, existing datasets and data-generation approaches are limited by static,…
Task-oriented dialogue (TOD) systems enable users to achieve their goals through natural language interactions. Traditionally, these systems have relied on turn-level manually annotated metadata, such as dialogue states and policy…
The development of artificial agents able to learn through dialog without domain restrictions has the potential to allow machines to learn how to perform tasks in a similar manner to humans and change how we relate to them. However,…
Task-Oriented Dialogue (TOD) systems are drawing more and more attention in recent studies. Current methods focus on constructing pre-trained models or fine-tuning strategies while the evaluation of TOD is limited by a policy mismatch…
Task-Oriented Dialogue (TOD) systems have become crucial components in interactive artificial intelligence applications. While recent advances have capitalized on pre-trained language models (PLMs), they exhibit limitations regarding…
Collecting data for training dialog systems can be extremely expensive due to the involvement of human participants and need for extensive annotation. Especially in document-grounded dialog systems, human experts need to carefully read the…
While the English virtual assistants have achieved exciting performance with an enormous amount of training resources, the needs of non-English-speakers have not been satisfied well. Up to Dec 2021, Alexa, one of the most popular smart…
Many everyday tasks, ranging from appliance repair and cooking to car maintenance, require expert knowledge, particularly for complex, multi-step procedures. Despite growing interest in AI agents for augmented reality (AR) assistance,…
Existing datasets for audio understanding primarily focus on single-turn interactions (i.e. audio captioning, audio question answering) for describing audio in natural language, thus limiting understanding audio via interactive dialogue. To…
Most prior work on task-oriented dialogue systems are restricted to limited coverage of domain APIs. However, users oftentimes have requests that are out of the scope of these APIs. This work focuses on responding to these…
Conversational agents have traditionally been developed for either task-oriented dialogue (TOD) or open-ended chitchat, with limited progress in unifying the two. Yet, real-world conversations naturally involve fluid transitions between…
In the field of natural language processing, open-domain chatbots have emerged as an important research topic. However, a major limitation of existing open-domain chatbot research is its singular focus on short single-session dialogue,…
Endowing a dialogue system with particular personality traits is essential to deliver more human-like conversations. However, due to the challenge of embodying personality via language expression and the lack of large-scale persona-labeled…
End-to-end generation-based approaches have been investigated and applied in task-oriented dialogue systems. However, in industrial scenarios, existing methods face the bottlenecks of controllability (e.g., domain-inconsistent responses,…
This paper analyzes some speed and performance improvement methods of Transformer architecture in recent years, mainly its application in dedicated model training. The dedicated model studied here refers to the open domain persona-aware…
Goal-oriented dialogue systems are now being widely adopted in industry where it is of key importance to maintain a rapid prototyping cycle for new products and domains. Data-driven dialogue system development has to be adapted to meet this…
Task-oriented dialogue (TOD) system is designed to accomplish user-defined tasks through dialogues. The TOD system has progressed towards end-to-end modeling by leveraging pre-trained large language models. Fine-tuning the pre-trained…
A commonly observed problem of the state-of-the-art natural language technologies, such as Amazon Alexa and Apple Siri, is that their services do not extend to most developing countries' citizens due to language barriers. Such populations…
This paper gives an overview of the Schema-Guided Dialogue State Tracking task of the 8th Dialogue System Technology Challenge. The goal of this task is to develop dialogue state tracking models suitable for large-scale virtual assistants,…