Mycal Tucker


2022

pdf bib
When Does Syntax Mediate Neural Language Model Performance? Evidence from Dropout Probes
Mycal Tucker | Tiwalayo Eisape | Peng Qian | Roger Levy | Julie Shah
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

Recent causal probing literature reveals when language models and syntactic probes use similar representations. Such techniques may yield “false negative” causality results: models may use representations of syntax, but probes may have learned to use redundant encodings of the same syntactic information. We demonstrate that models do encode syntactic information redundantly and introduce a new probe design that guides probes to consider all syntactic information present in embeddings. Using these probes, we find evidence for the use of syntax in models where prior methods did not, allowing us to boost model performance by injecting syntactic information into representations.

2021

pdf bib
What if This Modified That? Syntactic Interventions with Counterfactual Embeddings
Mycal Tucker | Peng Qian | Roger Levy
Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021