| 2024 | EACL | Leveraging Implicit Feedback from Deployment Data in Dialogue. | Richard Yuanzhe Pang, Stephen Roller, Kyunghyun Cho, He He, Jason Weston |
| 2023 | ICML | Scaling Laws for Generative Mixed-Modal Language Models. | Armen Aghajanyan, Lili Yu, Alexis Conneau, Wei-Ning Hsu, Karen Hambardzumyan, Susan Zhang, Stephen Roller, Naman Goyal, Omer Levy, Luke Zettlemoyer |
| 2023 | SIGdial | Enhancing Performance on Seen and Unseen Dialogue Scenarios using Retrieval-Augmented End-to-End Task-Oriented System. | Jianguo Zhang, Stephen Roller, Kun Qian, Zhiwei Liu, Rui Meng, Shelby Heinecke, Huan Wang, Silvio Savarese, Caiming Xiong |
| 2022 | EMNLP | Language Models that Seek for Knowledge: Modular Search & Generation for Dialogue and Prompt Completion. | Kurt Shuster, Mojtaba Komeili, Leonard Adolphs, Stephen Roller, Arthur Szlam, Jason Weston |
| 2021 | EACL | Recipes for Building an Open-Domain Chatbot. | Stephen Roller, Emily Dinan, Naman Goyal, Da Ju, Mary Williamson, Yinhan Liu, Jing Xu, Myle Ott, Eric Michael Smith, Y-Lan Boureau, Jason Weston |
| 2021 | ICML | Not All Memories are Created Equal: Learning to Forget by Expiring. | Sainbayar Sukhbaatar, Da Ju, Spencer Poff, Stephen Roller, Arthur Szlam, Jason Weston, Angela Fan |
| 2021 | NAACL | Adding Chit-Chat to Enhance Task-Oriented Dialogues. | Kai Sun, Seungwhan Moon, Paul A. Crook, Stephen Roller, Becka Silvert, Bing Liu, Zhiguang Wang, Honglei Liu, Eunjoon Cho, Claire Cardie |
| 2020 | ACL | Don't Say That! Making Inconsistent Dialogue Unlikely with Unlikelihood Training. | Margaret Li, Stephen Roller, Ilia Kulikov, Sean Welleck, Y-Lan Boureau, Kyunghyun Cho, Jason Weston |
| 2020 | ACL | The Dialogue Dodecathlon: Open-Domain Knowledge and Image Grounded Conversational Agents. | Kurt Shuster, Da Ju, Stephen Roller, Emily Dinan, Y-Lan Boureau, Jason Weston |
| 2020 | ICLR | Neural Text Generation With Unlikelihood Training. | Sean Welleck, Ilia Kulikov, Stephen Roller, Emily Dinan, Kyunghyun Cho, Jason Weston |
| 2019 | ACL | Inferring Concept Hierarchies from Text Corpora via Hyperbolic Embeddings. | Matt Le, Stephen Roller, Laetitia Papaxanthos, Douwe Kiela, Maximilian Nickel |
| 2019 | ICLR | Wizard of Wikipedia: Knowledge-Powered Conversational Agents. | Emily Dinan, Stephen Roller, Kurt Shuster, Angela Fan, Michael Auli, Jason Weston |
| 2019 | NAACL | What makes a good conversation? How controllable attributes affect human judgments. | Abigail See, Stephen Roller, Douwe Kiela, Jason Weston |
| 2018 | ACL | Hearst Patterns Revisited: Automatic Hypernym Detection from Large Text Corpora. | Stephen Roller, Douwe Kiela, Maximilian Nickel |
| 2017 | IJCNLP | Distributional Modeling on a Diet: One-shot Word Learning from Text Only. | Su Wang, Stephen Roller, Katrin Erk |
| 2016 | EMNLP | Relations such as Hypernymy: Identifying and Exploiting Hearst Patterns in Distributional Vectors for Lexical Entailment. | Stephen Roller, Katrin Erk |
| 2016 | NAACL | PIC a Different Word: A Simple Model for Lexical Substitution in Context. | Stephen Roller, Katrin Erk |
| 2016 | NAACL | MGNC-CNN: A Simple Approach to Exploiting Multiple Word Embeddings for Sentence Classification. | Ye Zhang, Stephen Roller, Byron C. Wallace |
| 2014 | COLING | Inclusive yet Selective: Supervised Distributional Hypernymy Detection. | Stephen Roller, Katrin Erk, Gemma Boleda |
| 2013 | EMNLP | A Multimodal LDA Model integrating Textual, Cognitive and Visual Modalities. | Stephen Roller, Sabine Schulte im Walde |
| 2012 | EMNLP | Supervised Text-based Geolocation Using Language Models on an Adaptive Grid. | Stephen Roller, Michael Speriosu, Sarat Rallapalli, Benjamin Wing, Jason Baldridge |
| 2011 | FDG | Automatic identification and generation of highlight cinematics for 3D games. | Mike Dominguez, R. Michael Young, Stephen Roller |