Related papers: TIAGE: A Benchmark for Topic-Shift Aware Dialog Mo…
Goal-oriented dialogue systems face a trade-off between fluent language generation and task-specific control. While supervised learning with large language models is capable of producing realistic text, how to steer such responses towards…
Automatically evaluating the quality of dialogue responses for unstructured domains is a challenging problem. Unfortunately, existing automatic evaluation metrics are biased and correlate very poorly with human judgements of response…
Generative models have advanced rapidly, enabling impressive talking head generation that brings AI to life. However, most existing methods focus solely on one-way portrait animation. Even the few that support bidirectional conversational…
Current conversational AI systems aim to understand a set of pre-designed requests and execute related actions, which limits them to evolve naturally and adapt based on human interactions. Motivated by how children learn their first…
Topic segmentation and labeling is often considered a prerequisite for higher-level conversation analysis and has been shown to be useful in many Natural Language Processing (NLP) applications. We present two new corpora of email and blog…
In open-domain conversational systems, it is important but challenging to leverage background knowledge. We can use the incorporation of knowledge to make the generation of dialogue controllable, and can generate more diverse sentences that…
The field of eXplainable Artificial Intelligence (XAI) is increasingly recognizing the need to personalize and/or interactively adapt the explanation to better reflect users' explanation needs. While dialogue-based approaches to XAI have…
Prior research has shown that typical fact-checking models for stand-alone claims struggle with claims made in dialogues. As a solution, fine-tuning these models on labelled dialogue data has been proposed. However, creating separate models…
Existing speech recognition systems are typically built at the sentence level, although it is known that dialog context, e.g. higher-level knowledge that spans across sentences or speakers, can help the processing of long conversations. The…
Task-oriented Dialog (ToD) systems have to solve multiple subgoals to accomplish user goals, whereas feedback is often obtained only at the end of the dialog. In this work, we propose SUIT (SUbgoal-aware ITerative Training), an iterative…
Machine learning approaches for building task-oriented dialogue systems require large conversational datasets with labels to train on. We are interested in building task-oriented dialogue systems from human-human conversations, which may be…
Medical dialogue generation aims to generate responses according to a history of dialogue turns between doctors and patients. Unlike open-domain dialogue generation, this requires background knowledge specific to the medical domain.…
An automated metric to evaluate dialogue quality is vital for optimizing data driven dialogue management. The common approach of relying on explicit user feedback during a conversation is intrusive and sparse. Current models to estimate…
Dialogue systems pretrained with large language models generate locally coherent responses, but lack the fine-grained control over responses necessary to achieve specific goals. A promising method to control response generation is…
Most prior work in dialogue modeling has been on written conversations mostly because of existing data sets. However, written dialogues are not sufficient to fully capture the nature of spoken conversations as well as the potential speech…
The predominant approach to open-domain dialog generation relies on end-to-end training of neural models on chat datasets. However, this approach provides little insight as to what these models learn (or do not learn) about engaging in…
Knowledge-grounded dialogue systems powered by large language models often generate responses that, while fluent, are not attributable to a relevant source of information. Progress towards models that do not exhibit this issue requires…
Conversation is ubiquitous in social life, but the empirical study of this interactive process has been thwarted by tools that are insufficiently modular and unadaptive to researcher needs. To relieve many constraints in conversation…
Most existing dialogue corpora and models have been designed to fit into 2 predominant categories : task-oriented dialogues portray functional goals, such as making a restaurant reservation or booking a plane ticket, while…
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…