🧑‍🔬 Douwe Kiela — all works

62 works · ← Douwe Kiela

1. Retrieval-Augmented Generation for Knowledge-Intensive NLP TasksarXiv:2005.11401Patrick Lewis, Ethan Perez, Aleksandra Piktus, et al.2020 · 6,256 citations
2. Personalizing Dialogue Agents: I have a dog, do you have pets too?Annual Meeting of the Association for Computational Linguistics (ACL)Saizheng Zhang, Emily Dinan, Jack Urbanek, et al.2018 · 1,854 citations
3. BLOOM: A 176B-Parameter Open-Access Multilingual Language Model ↗arXiv:2211.05100 · no summary yetBigScience Workshop et al.2022 · 1,606 citations
4. Adversarial NLI: A New Benchmark for Natural Language UnderstandingAnnual Meeting of the Association for Computational Linguistics (ACL)Yixin Nie, Adina Williams, Emily Dinan, et al.2020 · 1,296 citations
5. Supervised Learning of Universal Sentence Representations from Natural Language Inference DataConference on Empirical Methods in Natural Language Processing (EMNLP)Alexis Conneau, Douwe Kiela, Holger Schwenk, et al.2017 · 795 citations
6. SentEval: An Evaluation Toolkit for Universal Sentence RepresentationsLanguage Resources and Evaluation Conference (LREC)Alexis Conneau, Douwe Kiela2018 · 747 citations
7. FLAVA: A Foundational Language And Vision Alignment Model ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetAmanpreet Singh et al.2022 · 682 citations
8. The Second Conversational Intelligence Challenge (ConvAI2)arXiv:1902.00098Emily Dinan, Varvara Logacheva, Valentin Malykh, et al.2019 · 530 citations
9. Dynabench: Rethinking Benchmarking in NLP ↗Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · no summary yetDouwe Kiela et al.2021 · 482 citations
10. The Hateful Memes Challenge: Detecting Hate Speech in Multimodal MemesarXiv:2005.04790Douwe Kiela, Hamed Firooz, Aravind Mohan, et al.2020 · 420 citations
11. True Few-Shot Learning with Language ModelsarXiv:2105.11447Ethan Perez, Douwe Kiela, Kyunghyun Cho2021 · 412 citations
12. Retrieval Augmentation Reduces Hallucination in ConversationarXiv:2104.07567Kurt Shuster, Spencer Poff, Moya Chen, et al.2021 · 392 citations
13. What makes a good conversation? How controllable attributes affect human judgmentsConference of the North American Chapter of the Association for Computational Linguistics (NAACL)Abigail See, Stephen Roller, Douwe Kiela, et al.2019 · 374 citations
14. Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetTristan Thrush et al.2022 · 364 citations
15. Poincaré Embeddings for Learning Hierarchical RepresentationsarXiv:1705.08039Maximilian Nickel, Douwe Kiela2017 · 336 citations
16. KTO: Model Alignment as Prospect Theoretic Optimization ↗arXiv:2402.01306 · no summary yetKawin Ethayarajh et al.2024 · 333 citations
17. Learning from the Worst: Dynamically Generated Datasets to Improve Online Hate DetectionAnnual Meeting of the Association for Computational Linguistics (ACL)Bertie Vidgen, Tristan Thrush, Zeerak Waseem, et al.2021 · 325 citations
18. Masked Language Modeling and the Distributional Hypothesis: Order Word Matters Pre-training for LittleConference on Empirical Methods in Natural Language Processing (EMNLP)Koustuv Sinha, Robin Jia, Dieuwke Hupkes, et al.2021 · 297 citations
19. Black Holes and White Rabbits: Metaphor Identification with Visual FeaturesConference of the North American Chapter of the Association for Computational Linguistics (NAACL)Ekaterina Shutova, Douwe Kiela, Jean Maillard2016 · 293 citations
20. Queens are Powerful too: Mitigating Gender Bias in Dialogue GenerationConference on Empirical Methods in Natural Language Processing (EMNLP)Emily Dinan, Angela Fan, Adina Williams, et al.2020 · 270 citations
21. Learning to Speak and Act in a Fantasy Text Adventure Game ↗arXiv:1903.03094 · no summary yetJack Urbanek et al.2019 · 243 citations
22. Unsupervised Question Decomposition for Question AnsweringConference on Empirical Methods in Natural Language Processing (EMNLP)Ethan Perez, Patrick Lewis, Wen-tau Yih, et al.2020 · 222 citations
23. OBELICS: An Open Web-Scale Filtered Dataset of Interleaved Image-Text DocumentsConference on Neural Information Processing Systems (NeurIPS)Hugo Laurençon, Lucile Saulnier, Leo Tronchon, et al.2023 · 197 citations
24. Specializing Word Embeddings for Similarity or Relatedness ↗Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing · no summary yetDouwe Kiela, Felix Hill, Stephen Clark2015 · 191 citations
25. Gradient-based Adversarial Attacks against Text TransformersConference on Empirical Methods in Natural Language Processing (EMNLP)Chuan Guo, Alexandre Sablayrolles, Hervé Jégou, et al.2021 · 189 citations
26. Generative Representational Instruction TuningarXiv:2402.09906Niklas Muennighoff, Hongjin Su, Liang Wang, et al.2024 · 172 citations
27. Dynamic Meta-Embeddings for Improved Sentence Representations ↗Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing · no summary yetDouwe Kiela, Changhan Wang, Kyunghyun Cho2018 · 150 citations
28. HyperLex: A Large-Scale Evaluation of Graded Lexical EntailmentComputational LinguisticsIvan Vulić, Daniela Gerz, Douwe Kiela, et al.2017 · 148 citations
29. An Entropy-Based Model for Indoor Self-Localization Through Dialogue (Short Paper) ↗arXiv (Cornell University) · no summary yetHarm de Vries et al.2018 · 147 citations
30. Hearst Patterns Revisited: Automatic Hypernym Detection from Large Text Corpora ↗Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers) · no summary yetStephen Roller, Douwe Kiela, Maximilian Nickel2018 · 143 citations
31. Multi-Dimensional Gender Bias Classification ↗Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) · no summary yetEmily Dinan et al.2020 · 120 citations
32. Perturbation Augmentation for Fairer NLP ↗Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing · no summary yetRebecca Qian et al.2022 · 117 citations
33. Multi- and Cross-Modal Semantics Beyond Vision: Grounding in Auditory Perception ↗Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing · no summary yetDouwe Kiela, Stephen Clark2015 · 116 citations
34. Grasping the Finer Point: A Supervised Similarity Network for Metaphor Detection ↗Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing · no summary yetMarek Rei et al.2017 · 105 citations
35. DynaSent: A Dynamic Benchmark for Sentiment Analysis ↗Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) · no summary yetChristopher Potts et al.2021 · 103 citations
36. Learning Visually Grounded Sentence Representations ↗Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers) · no summary yetDouwe Kiela et al.2018 · 102 citations
37. I like fish, especially dolphins: Addressing Contradictions in Dialogue ModelingAnnual Meeting of the Association for Computational Linguistics (ACL)Yixin Nie, Mary Williamson, Mohit Bansal, et al.2021 · 101 citations
38. Generalized Inner Loop Meta-Learning ↗arXiv (Cornell University) · no summary yetEdward Grefenstette et al.2019 · 101 citations
39. Automatically Generating Rhythmic Verse with Neural Networks ↗Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · no summary yetJack Hopkins, Douwe Kiela2017 · 96 citations
40. Inferring Concept Hierarchies from Text Corpora via Hyperbolic Embeddings ↗Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics · no summary yetMatthew Le et al.2019 · 81 citations
41. Countering Language Drift via Visual Grounding ↗Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) · no summary yetJason Lee, Kyunghyun Cho, Douwe Kiela2019 · 77 citations
42. Emergent Translation in Multi-Agent Communication ↗arXiv (Cornell University) · no summary yetJason Lee et al.2017 · 62 citations
43. Dynaboard: An Evaluation-As-A-Service Platform for Holistic Next-Generation Benchmarking ↗arXiv (Cornell University) · no summary yetZhiyi Ma et al.2021 · 56 citations
44. Emergent Linguistic Phenomena in Multi-Agent Communication Games ↗Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) · no summary yetLaura Harding Graesser, Kyunghyun Cho, Douwe Kiela2019 · 54 citations
45. Emergent Communication in a Multi-Modal, Multi-Step Referential Game ↗arXiv (Cornell University) · no summary yetKatrina Evtimova et al.2017 · 52 citations
46. ANLIzing the Adversarial Natural Language Inference DatasetSociety for Computation in Linguistics (SCiL)Adina Williams, Tristan Thrush, Douwe Kiela2022 · 48 citations
47. Finding Generalizable Evidence by Learning to Convince Q&A ModelsConference on Empirical Methods in Natural Language Processing (EMNLP)Ethan Perez, Siddharth Karamcheti, Rob Fergus, et al.2019 · 43 citations
48. Code-Switched Named Entity Recognition with Embedding Attention ↗Proceedings of the Third Workshop on Computational Approaches to Linguistic Code-Switching · no summary yetChanghan Wang, Kyunghyun Cho, Douwe Kiela2018 · 43 citations
49. Human-Adversarial Visual Question Answering ↗arXiv (Cornell University) · no summary yetSasha Sheng et al.2021 · 40 citations
50. Jump to better conclusions: SCAN both left and rightEMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLPJasmijn Bastings, Marco Baroni, Jason Weston, et al.2018 · 38 citations
51. Anchor Points: Benchmarking Models with Much Fewer Examples ↗Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers) · no summary yetRajan Vivek et al.2024 · 33 citations
52. To what extent do human explanations of model behavior align with actual model behavior? ↗Proceedings of the Fourth BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP · no summary yetGrusha Prasad et al.2021 · 28 citations
53. Rissanen Data Analysis: Examining Dataset Characteristics via Description Length ↗arXiv (Cornell University) · no summary yetEthan Perez, Douwe Kiela, Kyunghyun Cho2021 · 22 citations
54. Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in AlignmentTransactions of the Association for Computational Linguistics (TACL)Karel D'Oosterlinck, Winnie Xu, Chris Develder, et al.2025 · 20 citations
55. The Hateful Memes Challenge: Competition Report ↗UvA-DARE (University of Amsterdam) · no summary yetDouwe Kiela et al.2020 · 20 citations
56. Mastering the Dungeon: Grounded Language Learning by Mechanical Turker Descent ↗arXiv (Cornell University) · no summary yetZhilin Yang et al.2017 · 17 citations
57. I am a Strange Dataset: Metalinguistic Tests for Language Models ↗Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · no summary yetTristan Thrush et al.2024 · 8 citations
58. Talk The Walk: Navigating Grids in New York City through Grounded Dialogue ↗no summary yetHarm de Vries et al.2018 · 5 citations
59. Countering Language Drift via Grounding ↗no summary yetJason Lee, Kyunghyun Cho, Douwe Kiela2018 · 3 citations
60. Contextualized Role Interaction for Neural Machine Translation ↗no summary yetDirk Weissenborn et al.2018 · 2 citations
61. Document Optimization for Black-Box Retrieval via Reinforcement Learning ↗arXiv (Cornell University) · no summary yetOmri Uzan et al.2026
62. RAGNET: End-to-end Training for Neural Graph Retrieval ↗Stanford Digital Repository · no summary yetSinha, Kunal et al.2025

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/douwe-kiela/works/