🧑‍🔬 Tal Linzen — all works

36 works · ← Tal Linzen

1. Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language InferenceR. Thomas McCoy, Ellie Pavlick, Tal LinzenEnglish · 1,662 citations
2. Assessing the Ability of LSTMs to Learn Syntax-Sensitive DependenciesTransactions of the Association for Computational Linguistics (TACL)Tal Linzen, Emmanuel Dupoux, Yoav Goldberg2016 · 1,256 citations
3. Colorless Green Recurrent Networks Dream HierarchicallyConference of the North American Chapter of the Association for Computational Linguistics (NAACL)Kristina Gulordava, Piotr Bojanowski, Edouard Grave, et al.2018 · 765 citations
4. Targeted Syntactic Evaluation of Language Models ↗Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing · no summary yetRebecca Marvin, Tal Linzen2018 · 641 citations
5. COGS: A Compositional Generalization Challenge Based on Semantic Interpretation ↗Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) · no summary yetNajoung Kim, Tal Linzen2020 · 328 citations
6. How Can We Accelerate Progress Towards Human-like Linguistic Generalization?Annual Meeting of the Association for Computational Linguistics (ACL)Tal Linzen2020 · 263 citations
7. Findings of the BabyLM Challenge: Sample-Efficient Pretraining on Developmentally Plausible Corpora ↗Proceedings of the BabyLM Challenge at the 27th Conference on Computational Natural Language Learning · no summary yetAlex Warstadt et al.2023 · 232 citations
8. Syntactic Data Augmentation Increases Robustness to Inference HeuristicsAnnual Meeting of the Association for Computational Linguistics (ACL)Junghyun Min, R. Thomas McCoy, Dipanjan Das, et al.2020 · 220 citations
9. Issues in evaluating semantic spaces using word analogies ↗Proceedings of the 1st Workshop on Evaluating Vector-Space Representations for NLP · no summary yetLinzen, Tal2016 · 198 citations
10. BERTs of a feather do not generalize together: Large variability in generalization across models with similar test set performance ↗Proceedings of the Third BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP · no summary yetR. Thomas McCoy, Junghyun Min, Tal Linzen2020 · 181 citations
11. Probing What Different NLP Tasks Teach Machines about Function Word ComprehensionJoint Conference on Lexical and Computational Semantics (*SEM)Najoung Kim, Roma Patel, Adam Poliak, et al.2019 · 163 citations
12. Does Syntax Need to Grow on Trees? Sources of Hierarchical Inductive Bias in Sequence-to-Sequence NetworksTransactions of the Association for Computational Linguistics (TACL)R. Thomas McCoy, Robert Frank, Tal Linzen2020 · 123 citations
13. How Much Do Language Models Copy From Their Training Data? Evaluating Linguistic Novelty in Text Generation Using RAVENTransactions of the Association for Computational Linguistics (TACL)R. Thomas McCoy, Paul Smolensky, Tal Linzen, et al.2023 · 117 citations
14. Quantity doesn't buy quality syntax with neural language models ↗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 yetMarten van Schijndel, Aaron Mueller, Tal Linzen2019 · 110 citations
15. Evaluating Attribution in Dialogue Systems: The BEGIN BenchmarkTransactions of the Association for Computational Linguistics (TACL)Nouha Dziri, Hannah Rashkin, Tal Linzen, et al.2022 · 100 citations
16. Cross-Linguistic Syntactic Evaluation of Word Prediction ModelsAnnual Meeting of the Association for Computational Linguistics (ACL)Aaron Mueller, Garrett Nicolai, Panayiota Petrou-Zeniou, et al.2020 · 98 citations
17. Frequency Effects on Syntactic Rule Learning in TransformersConference on Empirical Methods in Natural Language Processing (EMNLP)Jason Wei, Dan Garrette, Tal Linzen, et al.2021 · 92 citations
18. Counterfactual Interventions Reveal the Causal Effect of Relative Clause Representations on Agreement Prediction ↗Proceedings of the 25th Conference on Computational Natural Language Learning · no summary yetShauli Ravfogel et al.2021 · 89 citations
19. Studying the Inductive Biases of RNNs with Synthetic Variations of Natural LanguagesConference of the North American Chapter of the Association for Computational Linguistics (NAACL)Shauli Ravfogel, Yoav Goldberg, Tal Linzen2019 · 84 citations
20. Improving Compositional Generalization with Latent Structure and Data AugmentationConference of the North American Chapter of the Association for Computational Linguistics (NAACL)Linlu Qiu, Peter Shaw, Panupong Pasupat, et al.2022 · 76 citations
21. The reliability of acceptability judgments across languages ↗Glossa: a journal of general linguistics · no summary yetTal Linzen, Yohei Oseki2018 · 70 citations
22. The MultiBERTs: BERT Reproductions for Robustness Analysis ↗arXiv:2106.16163 · no summary yetThibault Sellam et al.2021 · 57 citations
23. How poor is the stimulus? Evaluating hierarchical generalization in neural networks trained on child-directed speechAnnual Meeting of the Association for Computational Linguistics (ACL)Aditya Yedetore, Tal Linzen, Robert Frank, et al.2023 · 49 citations
24. Does Putting a Linguist in the Loop Improve NLU Data Collection? ↗Findings of the Association for Computational Linguistics: EMNLP 2021 · no summary yetAlicia Parrish et al.2021 · 49 citations
25. NOPE: A Corpus of Naturally-Occurring Presuppositions in EnglishAlicia Parrish, Sebastian Schuster, Alex Warstadt, et al.English · 40 citations
26. How to Plant Trees in Language Models: Data and Architectural Effects on the Emergence of Syntactic Inductive Biases ↗arXiv:2305.19905 · no summary yetAaron Mueller, Tal Linzen2023 · 36 citations
27. Can You Learn Semantics Through Next-Word Prediction? The Case of Entailment ↗Findings of the Association for Computational Linguistics: ACL 2024 · no summary yetWilliam Merrill et al.2024 · 13 citations
28. Neural Networks Can Learn Patterns of Island-insensitivity in Norwegian ↗Proceedings of the Society for Computation in Linguistics 2023 · no summary yetAnastasia Kobzeva et al.2023 · 13 citations
29. Non-entailed subsequences as a challenge for natural language inferencearXiv:1811.12112R. Thomas McCoy, Tal Linzen2018 · 13 citations
30. What Goes Into a LM Acceptability Judgment? Rethinking the Impact of Frequency and LengthConference of the North American Chapter of the Association for Computational Linguistics (NAACL)Lindia Tjuatja, Graham Neubig, Tal Linzen, et al.2025 · 12 citations
31. Between Circuits and Chomsky: Pre-pretraining on Formal Languages Imparts Linguistic BiasesAnnual Meeting of the Association for Computational Linguistics (ACL)Michael Y. Hu, Jackson Petty, Chuan Shi, et al.2025 · 9 citations
32. Manipulating language models' training data to study syntactic constraint learning: the case of English passivizationarXiv:2407.04593Cara Su-Yi Leong, Tal Linzen2024 · 8 citations
33. Evaluating In-Context Translation with Synchronous Context-Free Grammar Transduction ↗arXiv:2604.07320 · no summary yetJackson Petty, Jaulie Goe, Tal Linzen2026 · 1 citation
34. LLM surprisal is necessary but not sufficient to capture English garden-path effects: Evidence from joint latent modeling of reading paradigmsarXiv:2602.04489Dario Paape, Tal Linzen, Shravan Vasishth2026
35. RELIC: Evaluating Complex Reasoning via the Recognition of Languages In-ContextTransactions of the Association for Computational Linguistics (TACL)Jackson Petty, Michael Y. Hu, Wentao Wang, et al.2026
36. Always Learning, Always Mixing: Efficient and Simple Data Mixing All The Time ↗arXiv (Cornell University) · no summary yetMichael Y. Hu et al.2026

↑ back to top

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