Y-Lan Boureau | DeepAI

DeepAI AI Chat

Featured Co-authors

Kyunghyun Cho
218 publications
Joelle Pineau
116 publications
Jason Weston
89 publications
Jing Xu
76 publications
Arthur Szlam
73 publications
Andrea Madotto
54 publications
Jakob Foerster
51 publications
Ronan Collobert
50 publications
Marc'Aurelio Ranzato
47 publications
Angela Fan
45 publications
Verena Rieser
42 publications

∙ 07/06/2023

Training Models to Generate, Recognize, and Reframe Unhelpful Thoughts

Many cognitive approaches to well-being, such as recognizing and reframi...

0 Mounica Maddela, et al. ∙

∙ 06/07/2023

The HCI Aspects of Public Deployment of Research Chatbots: A User Study, Design Recommendations, and Open Challenges

Publicly deploying research chatbots is a nuanced topic involving necess...

0 Morteza Behrooz, et al. ∙

∙ 06/07/2023

Improving Open Language Models by Learning from Organic Interactions

We present BlenderBot 3x, an update on the conversational model BlenderB...

0 Jing Xu, et al. ∙

∙ 08/05/2022

Learning from data in the mixed adversarial non-adversarial case: Finding the helpers and ignoring the trolls

The promise of interaction between intelligent conversational agents and...

6 Da Ju, et al. ∙

∙ 08/05/2022

Learning New Skills after Deployment: Improving open-domain internet-driven dialogue with human feedback

Frozen models trained to mimic static datasets can never improve their p...

9 Jing Xu, et al. ∙

∙ 08/05/2022

BlenderBot 3: a deployed conversational agent that continually learns to responsibly engage

We present BlenderBot 3, a 175B parameter dialogue model capable of open...

16 Kurt Shuster, et al. ∙

∙ 01/12/2022

Human Evaluation of Conversations is an Open Problem: comparing the sensitivity of various methods for evaluating dialogue agents

At the heart of improving conversational AI is the open problem of how t...

1 Eric Michael Smith, et al. ∙

∙ 10/14/2021

SaFeRDialogues: Taking Feedback Gracefully after Conversational Safety Failures

Current open-domain conversational models can easily be made to talk in ...

12 Megan Ung, et al. ∙

∙ 09/06/2021

Detecting Inspiring Content on Social Media

Inspiration moves a person to see new possibilities and transforms the w...

22 Oana Ignat, et al. ∙

∙ 07/07/2021

Anticipating Safety Issues in E2E Conversational AI: Framework and Tooling

Over the last several years, end-to-end neural conversational agents hav...

0 Emily Dinan, et al. ∙

∙ 12/30/2020

Linguistic calibration through metacognition: aligning dialogue agent responses with expected correctness

Open-domain dialogue agents have vastly improved, but still confidently ...

0 Sabrina J. Mielke, et al. ∙

∙ 10/14/2020

Recipes for Safety in Open-domain Chatbots

Models trained on large unlabeled corpora of human interactions will lea...

4 Jing Xu, et al. ∙

∙ 09/22/2020

Controlling Style in Generated Dialogue

Open-domain conversation models have become good at generating natural-s...

0 Eric Michael Smith, et al. ∙

∙ 06/22/2020

Open-Domain Conversational Agents: Current Progress, Open Problems, and Future Directions

We present our view of what is necessary to build an engaging open-domai...

19 Stephen Roller, et al. ∙

∙ 05/01/2020

Multi-scale Transformer Language Models

We investigate multi-scale transformer language models that learn repres...

0 Sandeep Subramanian, et al. ∙

∙ 04/28/2020

Recipes for building an open-domain chatbot

Building open-domain chatbots is a challenging area for machine learning...

6 Stephen Roller, et al. ∙

∙ 04/17/2020

Can You Put it All Together: Evaluating Conversational Agents' Ability to Blend Skills

Being engaging, knowledgeable, and empathetic are all desirable general ...

0 Eric Michael Smith, et al. ∙

∙ 12/28/2019

All-in-One Image-Grounded Conversational Agents

As single-task accuracy on individual language and image tasks has impro...

0 Da Ju, et al. ∙

∙ 11/10/2019

Zero-Shot Fine-Grained Style Transfer: Leveraging Distributed Continuous Style Representations to Transfer To Unseen Styles

Text style transfer is usually performed using attributes that can take ...

0 Eric Michael Smith, et al. ∙

∙ 11/10/2019

Don't Say That! Making Inconsistent Dialogue Unlikely with Unlikelihood Training

Generative dialogue models currently suffer from a number of problems wh...

0 Margaret Li, et al. ∙

∙ 11/09/2019

The Dialogue Dodecathlon: Open-Domain Knowledge and Image Grounded Conversational Agents

We introduce dodecaDialogue: a set of 12 tasks that measures if a conver...

0 Kurt Shuster, et al. ∙

∙ 09/09/2019

Recommendation as a Communication Game: Self-Supervised Bot-Play for Goal-oriented Dialogue

Traditional recommendation systems produce static rather than interactiv...

0 Dongyeop Kang, et al. ∙

∙ 03/12/2019

On the Pitfalls of Measuring Emergent Communication

How do we know if communication is emerging in a multi-agent system? The...

14 Ryan Lowe, et al. ∙

∙ 11/01/2018

Multiple-Attribute Text Style Transfer

The dominant approach to unsupervised "style transfer" in text is based ...

0 Sandeep Subramanian, et al. ∙

∙ 11/01/2018

I Know the Feeling: Learning to Converse with Empathy

Beyond understanding what is being discussed, human communication requir...

0 Hannah Rashkin, et al. ∙

∙ 05/24/2016

Learning End-to-End Goal-Oriented Dialog

Traditional dialog systems used in goal-oriented applications require a ...

0 Antoine Bordes, et al. ∙

Are you a researcher?
Expose your work
to one of the largest
A.I. communities in the world