Tal Linzen

Best Publications

• Right for the wrong reasons: Diagnosing syntactic heuristics in natural language inference

  R. Thomas McCoy;Ellie Pavlick;Tal Linzen

  1039
  Citations

• Assessing the Ability of LSTMs to Learn Syntax-Sensitive Dependencies

  Tal Linzen;Emmanuel Dupoux;Yoav Goldberg

  840
  Citations

• Targeted Syntactic Evaluation of Language Models

  Rebecca Marvin;Tal Linzen

  407
  Citations

• In Spoken Word Recognition, the Future Predicts the Past.

  Laura Gwilliams;Tal Linzen;David Poeppel;Alec Marantz;Alec Marantz

  195
  Citations

• COGS: A compositional generalization challenge based on semantic interpretation

  Najoung Kim;Tal Linzen

  167
  Citations

• Syntactic Data Augmentation Increases Robustness to Inference Heuristics

  Junghyun Min;R. Thomas McCoy;Dipanjan Das;Emily Pitler

  166
  Citations

• Uncertainty and Expectation in Sentence Processing: Evidence From Subcategorization Distributions

  Tal Linzen;T. Florian Jaeger

  141
  Citations

• BERTs of a feather do not generalize together: Large variability in generalization across models with similar test set performance

  R. Thomas McCoy;Junghyun Min;Tal Linzen

  123
  Citations

• Probing What Different NLP Tasks Teach Machines about Function Word Comprehension

  Najoung Kim;Roma Patel;Adam Poliak;Patrick Xia

  106
  Citations

• Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference

  R. Thomas McCoy;Ellie Pavlick;Tal Linzen

  93
  Citations

• Quantity doesn't buy quality syntax with neural language models

  Marten van Schijndel;Aaron Mueller;Tal Linzen

  85
  Citations

• The role of morphology in phoneme prediction: evidence from MEG.

  Allyson Ettinger;Allyson Ettinger;Tal Linzen;Alec Marantz

  77
  Citations

• Revisiting the poverty of the stimulus: hierarchical generalization without a hierarchical bias in recurrent neural networks.

  R. Thomas McCoy;Robert Frank;Tal Linzen

  76
  Citations

• Improving Compositional Generalization with Latent Structure and Data Augmentation

  Unknown

  74
  Citations

• Findings of the BabyLM Challenge: Sample-Efficient Pretraining on Developmentally Plausible Corpora

  Unknown

  65
  Citations

• Studying the inductive biases of RNNs with synthetic variations of natural languages

  Shauli Ravfogel;Yoav Goldberg;Yoav Goldberg;Tal Linzen

  61
  Citations

• In spoken word recognition the future predicts the past

  Laura Gwilliams;Tal Linzen;David Poeppel;Alec Marantz

  57
  Citations

• Modeling garden path effects without explicit hierarchical syntax.

  Marten van Schijndel;Tal Linzen

  55
  Citations

• Single-Stage Prediction Models Do Not Explain the Magnitude of Syntactic Disambiguation Difficulty.

  Marten van Schijndel;Tal Linzen

  54
  Citations

• The reliability of acceptability judgments across languages

  Tal Linzen;Yohei Oseki

  53
  Citations