publications

Please see Semantic Scholar for an up-to-date list of papers.

2023

  1. Pushdown Layers: Encoding Recursive Structure in Transformer Language Models
    Shikhar Murty, Pratyusha Sharma, Jacob Andreas, and Christopher Manning
    In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, Dec 2023
  2. Characterizing intrinsic compositionality in transformers with Tree Projections
    Shikhar Murty, Pratyusha Sharma, Jacob Andreas, and Christopher D Manning
    In The Eleventh International Conference on Learning Representations , Dec 2023
  3. Grokking of Hierarchical Structure in Vanilla Transformers
    Shikhar Murty, Pratyusha Sharma, Jacob Andreas, and Christopher D. Manning
    In Annual Meeting of the Association for Computational Linguistics, Dec 2023

2022

  1. On Measuring the Intrinsic Few-Shot Hardness of Datasets
    Xinran Zhao, Shikhar Murty, and Christopher D. Manning
    In Conference on Empirical Methods in Natural Language Processing, Dec 2022
  2. Fixing Model Bugs with Natural Language Patches
    Shikhar Murty, Christopher D. Manning, Scott M. Lundberg, and Marco Tulio Ribeiro
    In Conference on Empirical Methods in Natural Language Processing, Dec 2022

2021

  1. DReCa: A General Task Augmentation Strategy for Few-Shot Natural Language Inference
    Shikhar Murty, Tatsunori B. Hashimoto, and Christopher D. Manning
    In North American Chapter of the Association for Computational Linguistics, Dec 2021

2020

  1. ExpBERT: Representation Engineering with Natural Language Explanations
    Shikhar Murty, Pang Wei Koh, and Percy Liang
    In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, Jul 2020

2019

  1. Systematic Generalization: What Is Required and Can It Be Learned?
    Dzmitry Bahdanau*, Shikhar Murty*, Michael Noukhovitch, Thien Huu Nguyen, Harm Vries, and Aaron Courville
    In International Conference on Learning Representations, Jul 2019

2018

  1. Probabilistic Embedding of Knowledge Graphs with Box Lattice Measures
    Luke Vilnis*, Xiang Lorraine Li*, Shikhar Murty, and Andrew McCallum
    In Annual Meeting of the Association for Computational Linguistics, Jul 2018
  2. Hierarchical Losses and New Resources for Fine-grained Entity Typing and Linking
    Shikhar Murty, Patrick Verga, Luke Vilnis, Irena Radovanovic, and Andrew McCallum
    In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Jul 2018