Neural reality of argument structure constructions

1 code implementation • ACL 2022 • Bai Li, Zining Zhu, Guillaume Thomas, Frank Rudzicz, Yang Xu

Second, in a "Jabberwocky" priming-based experiment, we find that LMs associate ASCs with meaning, even in semantically nonsensical sentences.

Sentence

How is BERT surprised? Layerwise detection of linguistic anomalies

1 code implementation • ACL 2021 • Bai Li, Zining Zhu, Guillaume Thomas, Yang Xu, Frank Rudzicz

Transformer language models have shown remarkable ability in detecting when a word is anomalous in context, but likelihood scores offer no information about the cause of the anomaly.

Density Estimation

Word class flexibility: A deep contextualized approach

2 code implementations • EMNLP 2020 • Bai Li, Guillaume Thomas, Yang Xu, Frank Rudzicz

Word class flexibility refers to the phenomenon whereby a single word form is used across different grammatical categories.

Word Embeddings

Word order variation in Mby\'a Guaran\'\i

no code implementations • WS 2019 • Angelika Kiss, Guillaume Thomas

Universal Dependencies for Mby\'a Guaran\'\i

no code implementations • WS 2019 • Guillaume Thomas