When classifying arguments, BERT doesn’t care about word order...except when it matters

By Isabel Papadimitriou, Richard Futrell, Kyle Mahowald. 2022

Subfields: Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Natural Language Processing

1. Andrew Kyle Lampinen
2. James L. McClelland
3. Felix Hill
4. Jane X. Wang
5. Kory Matthewson
6. Antonia Creswell
7. Michael Henry Tessler
8. Ishita Dasgupta

Citations in the corpus

• Can language models learn from explanations in context? (2022, background): “One possible reconciliation with past findings is that the models are “lazy” and rely on low-level features when they can, and only use higher-level relationships in challenging settings that require them (cf. Papadimitriou et al., 2022).”