Related papers: What makes a good conversation? How controllable a…
Natural Language Generation (NLG) for task-oriented dialogue systems focuses on communicating specific content accurately, fluently, and coherently. While these attributes are crucial for a successful dialogue, it is also desirable to…
The amount of dialogue history to include in a conversational agent is often underestimated and/or set in an empirical and thus possibly naive way. This suggests that principled investigations into optimal context windows are urgently…
Large language models (LLMs) are powerful dialogue agents, but specializing them towards fulfilling a specific function can be challenging. Instructing tuning, i.e. tuning models on instruction and sample responses generated by humans…
The study illustrates a first step towards an ongoing work aimed at developing a dataset of dialogues potentially useful for customer service conversation management between humans and AI chatbots. The approach exploits ChatGPT 3.5 to…
Evaluating open-domain dialogue systems is difficult due to the diversity of possible correct answers. Automatic metrics such as BLEU correlate weakly with human annotations, resulting in a significant bias across different models and…
Accurate automatic evaluation metrics for open-domain dialogs are in high demand. Existing model-based metrics for system response evaluation are trained on human annotated data, which is cumbersome to collect. In this work, we propose to…
We study improving social conversational agents by learning from natural dialogue between users and a deployed model, without extra annotations. To implicitly measure the quality of a machine-generated utterance, we leverage signals like…
Debate is the process of exchanging viewpoints or convincing others on a particular issue. Recent research has provided empirical evidence that the persuasiveness of an argument is determined not only by language usage but also by…
Human ratings are one of the most prevalent methods to evaluate the performance of natural language processing algorithms. Similarly, it is common to measure the quality of sentences generated by a natural language generation model using…
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…
User attributes provide rich and useful information for user understanding, yet structured and easy-to-use attributes are often sparsely populated. In this paper, we leverage dialogues with conversational agents, which contain strong…
We investigate the task of modeling open-domain, multi-turn, unstructured, multi-participant, conversational dialogue. We specifically study the effect of incorporating different elements of the conversation. Unlike previous efforts, which…
High-fidelity, AI-based simulated classroom systems enable teachers to rehearse effective teaching strategies. However, dialogue-oriented open-ended conversations such as teaching a student about scale factors can be difficult to model.…
Developing intelligent persuasive conversational agents to change people's opinions and actions for social good is the frontier in advancing the ethical development of automated dialogue systems. To do so, the first step is to understand…
Measurement of interaction quality is a critical task for the improvement of spoken dialog systems. Existing approaches to dialog quality estimation either focus on evaluating the quality of individual turns, or collect dialog-level quality…
Conversational systems or chatbots are an example of AI-Infused Applications (AIIA). Chatbots are especially important as they are often the first interaction of clients with a business and are the entry point of a business into the AI…
Large-scale dialogue datasets have recently become available for training neural dialogue agents. However, these datasets have been reported to contain a non-negligible number of unacceptable utterance pairs. In this paper, we propose a…
This thesis investigates the controllability of deep learning-based, end-to-end, generative dialogue systems in both task-oriented and chit-chat scenarios. In particular, we study the different aspects of controlling generative dialogue…
With the ongoing penetration of conversational user interfaces, a better understanding of social and emotional characteristic inherent to dialogue is required. Chatbots in particular face the challenge of conveying human-like behaviour…
One critical issue for chat systems is to stay consistent about preferences, opinions, beliefs and facts of itself, which has been shown a difficult problem. In this work, we study methods to assess and bolster utterance consistency of chat…