Stephen Roller
Stephen Roller
Facebook AI Research
Verified email at - Homepage
Cited by
Cited by
Wizard of wikipedia: Knowledge-powered conversational agents
E Dinan, S Roller, K Shuster, A Fan, M Auli, J Weston
arXiv preprint arXiv:1811.01241, 2018
Supervised Text-based Geolocation Using Language Models on an Adaptive Grid
S Roller, M Speriosu, S Rallapalli, B Wing, J Baldridge
Recipes for building an open-domain chatbot
S Roller, E Dinan, N Goyal, D Ju, M Williamson, Y Liu, J Xu, M Ott, ...
arXiv preprint arXiv:2004.13637, 2020
Inclusive yet selective: Supervised distributional hypernymy detection
S Roller, K Erk, G Boleda
Proceedings of COLING 2014, the 25th International Conference on …, 2014
Neural text generation with unlikelihood training
S Welleck, I Kulikov, S Roller, E Dinan, K Cho, J Weston
arXiv preprint arXiv:1908.04319, 2019
MGNC-CNN: A simple approach to exploiting multiple word embeddings for sentence classification
Y Zhang, S Roller, B Wallace
arXiv preprint arXiv:1603.00968, 2016
What makes a good conversation? how controllable attributes affect human judgments
A See, S Roller, D Kiela, J Weston
arXiv preprint arXiv:1902.08654, 2019
A multimodal LDA model integrating textual, cognitive and visual modalities
S Roller, SS Im Walde
Proceedings of the 2013 Conference on Empirical Methods in Natural Language …, 2013
Hearst patterns revisited: Automatic hypernym detection from large text corpora
S Roller, D Kiela, M Nickel
arXiv preprint arXiv:1806.03191, 2018
Relations such as hypernymy: Identifying and exploiting hearst patterns in distributional vectors for lexical entailment
S Roller, K Erk
arXiv preprint arXiv:1605.05433, 2016
Representing meaning with a combination of logical and distributional models
I Beltagy, S Roller, P Cheng, K Erk, RJ Mooney
Computational Linguistics 42 (4), 763-808, 2016
Acute-eval: Improved dialogue evaluation with optimized questions and multi-turn comparisons
M Li, J Weston, S Roller
arXiv preprint arXiv:1909.03087, 2019
Don't Say That! Making Inconsistent Dialogue Unlikely with Unlikelihood Training
M Li, S Roller, I Kulikov, S Welleck, YL Boureau, K Cho, J Weston
arXiv preprint arXiv:1911.03860, 2019
Exploring vector space models to predict the compositionality of German noun-noun compounds
SS Im Walde, S Müller, S Roller
Second Joint Conference on Lexical and Computational Semantics (* SEM …, 2013
Inferring concept hierarchies from text corpora via hyperbolic embeddings
M Le, S Roller, L Papaxanthos, D Kiela, M Nickel
arXiv preprint arXiv:1902.00913, 2019
The dialogue dodecathlon: Open-domain knowledge and image grounded conversational agents
K Shuster, D Ju, S Roller, E Dinan, YL Boureau, J Weston
arXiv preprint arXiv:1911.03768, 2019
Open-domain conversational agents: Current progress, open problems, and future directions
S Roller, YL Boureau, J Weston, A Bordes, E Dinan, A Fan, D Gunning, ...
arXiv preprint arXiv:2006.12442, 2020
PIC a different word: A simple model for lexical substitution in context
S Roller, K Erk
Proceedings of the 2016 Conference of the North American Chapter of the …, 2016
Utexas: Natural language semantics using distributional semantics and probabilistic logic
I Beltagy, S Roller, G Boleda, K Erk, R Mooney
Proceedings of the 8th International Workshop on Semantic Evaluation …, 2014
The (un) expected effects of applying standard cleansing models to human ratings on compositionality
S Roller, SS im Walde, S Scheible
Proceedings of the 9th Workshop on Multiword Expressions, 32-41, 2013
The system can't perform the operation now. Try again later.
Articles 1–20