Stephen Roller

58 papers A* 9A 1B 2C 1Journal 28Unranked 17

Year	Rank	Type	Title / Venue / Authors
2024	—	`conf`	Leveraging Implicit Feedback from Deployment Data in Dialogue. EACL (2) Richard Yuanzhe Pang, Stephen Roller, Kyunghyun Cho, He He, Jason Weston
2023	J	`jnl`	A Theory on Adam Instability in Large-Scale Machine Learning. CoRR Igor Molybog, Peter Albert, Moya Chen, Zachary DeVito, David Esiobu, Naman Goyal, Punit Singh Koura, Sharan Narang, Andrew Poulton, Ruan Silva, Binh Tang, Diana Liskovich, Puxin Xu, Yuchen Zhang, Melanie Kambadur, Stephen Roller, Susan Zhang
2023	B	`conf`	Enhancing Performance on Seen and Unseen Dialogue Scenarios using Retrieval-Augmented End-to-End Task-Oriented System. SIGDIAL Jianguo Zhang, Stephen Roller, Kun Qian, Zhiwei Liu, Rui Meng, Shelby Heinecke, Huan Wang, Silvio Savarese, Caiming Xiong
2023	J	`jnl`	Enhancing Performance on Seen and Unseen Dialogue Scenarios using Retrieval-Augmented End-to-End Task-Oriented System. CoRR Jianguo Zhang, Stephen Roller, Kun Qian, Zhiwei Liu, Rui Meng, Shelby Heinecke, Huan Wang, Silvio Savarese, Caiming Xiong
2023	J	`jnl`	Leveraging Implicit Feedback from Deployment Data in Dialogue. CoRR Richard Yuanzhe Pang, Stephen Roller, Kyunghyun Cho, He He, Jason Weston
2023	A*	`conf`	Scaling Laws for Generative Mixed-Modal Language Models. ICML Armen Aghajanyan, Lili Yu, Alexis Conneau, Wei-Ning Hsu, Karen Hambardzumyan, Susan Zhang, Stephen Roller, Naman Goyal, Omer Levy, Luke Zettlemoyer
2023	J	`jnl`	Scaling Laws for Generative Mixed-Modal Language Models. CoRR Armen Aghajanyan, Lili Yu, Alexis Conneau, Wei-Ning Hsu, Karen Hambardzumyan, Susan Zhang, Stephen Roller, Naman Goyal, Omer Levy, Luke Zettlemoyer
2022	J	`jnl`	BlenderBot 3: a deployed conversational agent that continually learns to responsibly engage. CoRR Kurt Shuster, Jing Xu, Mojtaba Komeili, Da Ju, Eric Michael Smith, Stephen Roller, Megan Ung, Moya Chen, Kushal Arora, Joshua Lane, Morteza Behrooz, William Ngan, Spencer Poff, Naman Goyal, Arthur Szlam, Y-Lan Boureau, Melanie Kambadur, Jason Weston
2022	—	`conf`	Human Evaluation of Conversations is an Open Problem: comparing the sensitivity of various methods for evaluating dialogue agents. ConvAI@ACL Eric Michael Smith, Orion Hsu, Rebecca Qian, Stephen Roller, Y-Lan Boureau, Jason Weston
2022	J	`jnl`	Human Evaluation of Conversations is an Open Problem: comparing the sensitivity of various methods for evaluating dialogue agents. CoRR Eric Michael Smith, Orion Hsu, Rebecca Qian, Stephen Roller, Y-Lan Boureau, Jason Weston
2022	—	`conf`	Language Models that Seek for Knowledge: Modular Search & Generation for Dialogue and Prompt Completion. EMNLP (Findings) Kurt Shuster, Mojtaba Komeili, Leonard Adolphs, Stephen Roller, Arthur Szlam, Jason Weston
2022	J	`jnl`	Language Models that Seek for Knowledge: Modular Search & Generation for Dialogue and Prompt Completion. CoRR Kurt Shuster, Mojtaba Komeili, Leonard Adolphs, Stephen Roller, Arthur Szlam, Jason Weston
2022	J	`jnl`	OPT: Open Pre-trained Transformer Language Models. CoRR Susan Zhang, Stephen Roller, Naman Goyal, Mikel Artetxe, Moya Chen, Shuohui Chen, Christopher Dewan, Mona T. Diab, Xian Li, Xi Victoria Lin, Todor Mihaylov, Myle Ott, Sam Shleifer, Kurt Shuster, Daniel Simig, Punit Singh Koura, Anjali Sridhar, Tianlu Wang, Luke Zettlemoyer
2022	A*	`conf`	Staircase Attention for Recurrent Processing of Sequences. NeurIPS Da Ju, Stephen Roller, Sainbayar Sukhbaatar, Jason Weston
2021	—	`conf`	Adding Chit-Chat to Enhance Task-Oriented Dialogues. NAACL-HLT Kai Sun, Seungwhan Moon, Paul A. Crook, Stephen Roller, Becka Silvert, Bing Liu, Zhiguang Wang, Honglei Liu, Eunjoon Cho, Claire Cardie
2021	A*	`conf`	Hash Layers For Large Sparse Models. NeurIPS Stephen Roller, Sainbayar Sukhbaatar, Arthur Szlam, Jason Weston
2021	J	`jnl`	Hash Layers For Large Sparse Models. CoRR Stephen Roller, Sainbayar Sukhbaatar, Arthur Szlam, Jason Weston
2021	A*	`conf`	Not All Memories are Created Equal: Learning to Forget by Expiring. ICML Sainbayar Sukhbaatar, Da Ju, Spencer Poff, Stephen Roller, Arthur Szlam, Jason Weston, Angela Fan
2021	J	`jnl`	Not All Memories are Created Equal: Learning to Forget by Expiring. CoRR Sainbayar Sukhbaatar, Da Ju, Spencer Poff, Stephen Roller, Arthur Szlam, Jason Weston, Angela Fan
2021	A	`conf`	Recipes for Building an Open-Domain Chatbot. EACL 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	J	`jnl`	Staircase Attention for Recurrent Processing of Sequences. CoRR Da Ju, Stephen Roller, Sainbayar Sukhbaatar, Jason Weston
2021	J	`jnl`	Teaching Models new APIs: Domain-Agnostic Simulators for Task Oriented Dialogue. CoRR Moya Chen, Paul A. Crook, Stephen Roller
2020	J	`jnl`	Adding Chit-Chats to Enhance Task-Oriented Dialogues. CoRR Kai Sun, Seungwhan Moon, Paul A. Crook, Stephen Roller, Becka Silvert, Bing Liu, Zhiguang Wang, Honglei Liu, Eunjoon Cho, Claire Cardie
2020	A*	`conf`	Don't Say That! Making Inconsistent Dialogue Unlikely with Unlikelihood Training. ACL Margaret Li, Stephen Roller, Ilia Kulikov, Sean Welleck, Y-Lan Boureau, Kyunghyun Cho, Jason Weston
2020	A*	`conf`	Neural Text Generation With Unlikelihood Training. ICLR Sean Welleck, Ilia Kulikov, Stephen Roller, Emily Dinan, Kyunghyun Cho, Jason Weston
2020	J	`jnl`	Open-Domain Conversational Agents: Current Progress, Open Problems, and Future Directions. CoRR Stephen Roller, Y-Lan Boureau, Jason Weston, Antoine Bordes, Emily Dinan, Angela Fan, David Gunning, Da Ju, Margaret Li, Spencer Poff, Pratik Ringshia, Kurt Shuster, Eric Michael Smith, Arthur Szlam, Jack Urbanek, Mary Williamson
2020	J	`jnl`	Recipes for building an open-domain chatbot. CoRR Stephen Roller, Emily Dinan, Naman Goyal, Da Ju, Mary Williamson, Yinhan Liu, Jing Xu, Myle Ott, Kurt Shuster, Eric Michael Smith, Y-Lan Boureau, Jason Weston
2020	A*	`conf`	The Dialogue Dodecathlon: Open-Domain Knowledge and Image Grounded Conversational Agents. ACL Kurt Shuster, Da Ju, Stephen Roller, Emily Dinan, Y-Lan Boureau, Jason Weston
2019	J	`jnl`	ACUTE-EVAL: Improved Dialogue Evaluation with Optimized Questions and Multi-turn Comparisons. CoRR Margaret Li, Jason Weston, Stephen Roller
2019	J	`jnl`	Don't Say That! Making Inconsistent Dialogue Unlikely with Unlikelihood Training. CoRR Margaret Li, Stephen Roller, Ilia Kulikov, Sean Welleck, Y-Lan Boureau, Kyunghyun Cho, Jason Weston
2019	—	`conf`	Inferring Concept Hierarchies from Text Corpora via Hyperbolic Embeddings. ACL (1) Matt Le, Stephen Roller, Laetitia Papaxanthos, Douwe Kiela, Maximilian Nickel
2019	J	`jnl`	Inferring Concept Hierarchies from Text Corpora via Hyperbolic Embeddings. CoRR Matt Le, Stephen Roller, Laetitia Papaxanthos, Douwe Kiela, Maximilian Nickel
2019	J	`jnl`	Neural Text Generation with Unlikelihood Training. CoRR Sean Welleck, Ilia Kulikov, Stephen Roller, Emily Dinan, Kyunghyun Cho, Jason Weston
2019	J	`jnl`	The Dialogue Dodecathlon: Open-Domain Knowledge and Image Grounded Conversational Agents. CoRR Kurt Shuster, Da Ju, Stephen Roller, Emily Dinan, Y-Lan Boureau, Jason Weston
2019	—	`conf`	What makes a good conversation? How controllable attributes affect human judgments. NAACL-HLT (1) Abigail See, Stephen Roller, Douwe Kiela, Jason Weston
2019	J	`jnl`	What makes a good conversation? How controllable attributes affect human judgments. CoRR Abigail See, Stephen Roller, Douwe Kiela, Jason Weston
2019	—	`conf`	Wizard of Wikipedia: Knowledge-Powered Conversational Agents. ICLR (Poster) Emily Dinan, Stephen Roller, Kurt Shuster, Angela Fan, Michael Auli, Jason Weston
2018	—	`conf`	Hearst Patterns Revisited: Automatic Hypernym Detection from Large Text Corpora. ACL (2) Stephen Roller, Douwe Kiela, Maximilian Nickel
2018	J	`jnl`	Hearst Patterns Revisited: Automatic Hypernym Detection from Large Text Corpora. CoRR Stephen Roller, Douwe Kiela, Maximilian Nickel
2018	J	`jnl`	Wizard of Wikipedia: Knowledge-Powered Conversational agents. CoRR Emily Dinan, Stephen Roller, Kurt Shuster, Angela Fan, Michael Auli, Jason Weston
2017	—	`conf`	Distributional Modeling on a Diet: One-shot Word Learning from Text Only. IJCNLP(1) Su Wang, Stephen Roller, Katrin Erk
2017	J	`jnl`	Distributional model on a diet: One-shot word learning from text only. CoRR Su Wang, Stephen Roller, Katrin Erk
2016	—	`conf`	MGNC-CNN: A Simple Approach to Exploiting Multiple Word Embeddings for Sentence Classification. HLT-NAACL Ye Zhang, Stephen Roller, Byron C. Wallace
2016	J	`jnl`	MGNC-CNN: A Simple Approach to Exploiting Multiple Word Embeddings for Sentence Classification. CoRR Ye Zhang, Stephen Roller, Byron C. Wallace
2016	—	`conf`	PIC a Different Word: A Simple Model for Lexical Substitution in Context. HLT-NAACL Stephen Roller, Katrin Erk
2016	A*	`conf`	Relations such as Hypernymy: Identifying and Exploiting Hearst Patterns in Distributional Vectors for Lexical Entailment. EMNLP Stephen Roller, Katrin Erk
2016	J	`jnl`	Relations such as Hypernymy: Identifying and Exploiting Hearst Patterns in Distributional Vectors for Lexical Entailment. CoRR Stephen Roller, Katrin Erk
2016	J	`jnl`	Representing Meaning with a Combination of Logical and Distributional Models. Comput. Linguistics Islam Beltagy, Stephen Roller, Pengxiang Cheng, Katrin Erk, Raymond J. Mooney
2015	J	`jnl`	Representing Meaning with a Combination of Logical Form and Vectors. CoRR Islam Beltagy, Stephen Roller, Pengxiang Cheng, Katrin Erk, Raymond J. Mooney
2014	—	`conf`	Feature Norms of German Noun Compounds. MWE@EACL Stephen Roller, Sabine Schulte im Walde
2014	B	`conf`	Inclusive yet Selective: Supervised Distributional Hypernymy Detection. COLING Stephen Roller, Katrin Erk, Gemma Boleda
2014	—	`conf`	UTexas: Natural Language Semantics using Distributional Semantics and Probabilistic Logic. SemEval@COLING Islam Beltagy, Stephen Roller, Gemma Boleda, Katrin Erk, Raymond J. Mooney
2013	A*	`conf`	A Multimodal LDA Model integrating Textual, Cognitive and Visual Modalities. EMNLP Stephen Roller, Sabine Schulte im Walde
2013	—	`conf`	Exploring Vector Space Models to Predict the Compositionality of German Noun-Noun Compounds. *SEM@NAACL-HLT Sabine Schulte im Walde, Stefan Müller, Stephen Roller
2013	—	`conf`	The (Un)expected Effects of Applying Standard Cleansing Models to Human Ratings on Compositionality. MWE@NAACL-HLT Stephen Roller, Sabine Schulte im Walde, Silke Scheible
2012	—	`conf`	Supervised Text-based Geolocation Using Language Models on an Adaptive Grid. EMNLP-CoNLL Stephen Roller, Michael Speriosu, Sarat Rallapalli, Benjamin Wing, Jason Baldridge
2011	C	`conf`	Automatic identification and generation of highlight cinematics for 3D games. FDG Mike Dominguez, R. Michael Young, Stephen Roller
2011	—	`conf`	Design and Evaluation of Afterthought, A System that Automatically Creates Highlight Cinematics for 3D Games. AIIDE Mike Dominguez, R. Michael Young, Stephen Roller