Papers by Y-Lan Boureau
Reducing Conversational Agents’ Overconfidence Through Linguistic Calibration (2022.tacl-1)
Copied to clipboard
| Challenge: | Neural generative open-domain english-language dialogue agents are currently unsuitable for applications other than entertainement and research. |
| Approach: | They propose to incorporate metacognitive features into the training of a controllable generation model to improve likelihood of correctness. |
| Outcome: | The proposed model improves likelihood of correctness by incorporating metacognitive features into the training of a controllable generation model. |
Recipes for Building an Open-Domain Chatbot (2021.eacl-main)
Copied to clipboard
Stephen Roller, Emily Dinan, Naman Goyal, Da Ju, Mary Williamson, Yinhan Liu, Jing Xu, Myle Ott, Eric Michael Smith, Y-Lan Boureau, Jason Weston
| Challenge: | Existing work shows that scaling models in the number of parameters and the size of the data they are trained on gives improved results, but other factors are important. |
| Approach: | They propose to build open-domain chatbots that can be scaled to improve their performance . they use a blend of cognitive and cognitive skills to build a model that combines these skills . |
| Outcome: | The proposed models outperform existing approaches in multi-turn dialogue on engagingness and humanness measurements. |
Towards Empathetic Open-domain Conversation Models: A New Benchmark and Dataset (P19-1)
Copied to clipboard
| Challenge: | EmpatheticDialogues dataset provides a benchmark for empathetic dialogue generation . human evaluators perceive dialogue models as more epathetic . |
| Approach: | They propose a benchmark for empathetic dialogue generation from a dataset of 25k conversations grounded in emotional situations. |
| Outcome: | The proposed benchmarks show that existing models are perceived to be more empathetic by human evaluators compared to models trained on large-scale Internet conversations. |
Don’t Say That! Making Inconsistent Dialogue Unlikely with Unlikelihood Training (2020.acl-main)
Copied to clipboard
| Challenge: | Unlikelihood is a technique developed for removal of repetition in language model completions . it allows for a model to be generalized to solve a number of problems . |
| Approach: | They extend the unlikelihood objective to generate generations that contain repetitions . they show that such an objective can be used to improve logical consistency . |
| Outcome: | The proposed approach can be applied to a number of dialogue tasks. |
Recommendation as a Communication Game: Self-Supervised Bot-Play for Goal-oriented Dialogue (D19-1)
Copied to clipboard
| Challenge: | Traditional recommendation systems produce static rather than interactive recommendations invariant to a user’s specific requests, clarifications, or current mood. |
| Approach: | They use a goal-driven recommendation dialogue dataset to develop an end-to-end dialogue system that can simultaneously converse and recommend. |
| Outcome: | The proposed system can converse and recommend movies to humans without considering the task goal itself. |
The Dialogue Dodecathlon: Open-Domain Knowledge and Image Grounded Conversational Agents (2020.acl-main)
Copied to clipboard
| Challenge: | a set of 12 tasks that measure if a conversational agent can communicate engagingly with personality and empathy, ask questions, answer questions by utilizing knowledge resources, and perceive and converse about images. |
| Approach: | They propose a set of 12 tasks that measure if a conversational agent can communicate engagingly with personality and empathy . they use large dialogue datasets to multi-task and obtain state-of-the-art results . |
| Outcome: | The proposed model improves over a BERT pre-trained model on large dialogue datasets and provides state-of-the-art results on many of the tasks. |
Can You Put it All Together: Evaluating Conversational Agents’ Ability to Blend Skills (2020.acl-main)
Copied to clipboard
| Challenge: | Existing work has focused on learning specific qualities of conversational agents, but it remains unclear how to combine them. |
| Approach: | They propose to combine models trained towards isolated capabilities with multi-task training to improve conversation performance. |
| Outcome: | The proposed dataset compares models trained towards isolated capabilities with models trained on a single skill. |
Training Models to Generate, Recognize, and Reframe Unhelpful Thoughts (2023.acl-long)
Copied to clipboard
| Challenge: | Existing models for cognitive behavioral therapy lack specific and diverse practice material. |
| Approach: | They propose to use a dataset to generate unhelpful thought patterns . they propose to train and evaluate existing models to generate an abundance of practice material . |
| Outcome: | The proposed model can generate unlimited quantity of practice material and generate suitable reframing proposals with no or minimal additional model training required. |
SaFeRDialogues: Taking Feedback Gracefully after Conversational Safety Failures (2022.acl-long)
Copied to clipboard
| Challenge: | Existing open-domain conversational models can easily be made to talk in inadequate ways. |
| Approach: | They propose a task and dataset of graceful responses to safety feedback . they collect 8k dialogues demonstrating safety failures, feedback signaling them, and a response acknowledging feedback. |
| Outcome: | The proposed model improves on a dataset of 8k dialogues demonstrating safety failures, feedback signaling them, and a response acknowledging the feedback. |
Bot-Adversarial Dialogue for Safe Conversational Agents (2021.naacl-main)
Copied to clipboard
| Challenge: | a new method for evaluating chatbot safety is proposed to mimic human-generated data . a bot-adversarial dialogue model learns undesirable features from this data, a study finds . |
| Approach: | They propose a human-and-model-in-the-loop framework for evaluating toxicity of chatbots . they propose two methods for safe conversational agents by either training on data or ”baking-in” safety to the generative model itself. |
| Outcome: | The proposed methods are safer than existing models while maintaining usability metrics, the authors say . they show that the proposed methods can be used to make safer models with human-model interactions . |
SafetyKit: First Aid for Measuring Safety in Open-domain Conversational Systems (2022.acl-long)
Copied to clipboard
| Challenge: | Several studies discuss the potential harms and benefits of large language models (LLMs) large neural models can replicate and even amplify negative, stereotypical, and derogatory associations in the data. |
| Approach: | They propose to use a first aid kit to assess the safety of conversational AI in various settings . they propose several future directions and discuss ethical considerations . |
| Outcome: | The proposed tools can provide estimates of the relative safety of systems in various settings, but they still have several shortcomings. |
Revisiting the Evaluation of Theory of Mind through Question Answering (D19-1)
Copied to clipboard
| Challenge: | Existing benchmarks for theory of mind are flawed due to dataset biases . evaluators have been using the Sally-Anne test to infer false beliefs in others . |
| Approach: | They propose to use question answering to evaluate theory of mind . they propose to explicitly control for data regularities via a careful examination of the answer space . |
| Outcome: | The proposed evaluation protocol and dataset control for data regularities via a careful examination of the answer space. |
Learning New Skills after Deployment: Improving open-domain internet-driven dialogue with human feedback (2023.acl-long)
Copied to clipboard
| Challenge: | Frozen models trained to mimic static datasets can never improve their performance. |
| Approach: | They propose to use binary quality measurements and free-form text feedback to improve conversational skills in a conversational learning framework. |
| Outcome: | The proposed model improves on the DIRECTOR model, which is based on binary quality measurements and free-form text feedback, and shows that iterative retraining and redeployment can improve the model. |