research
∙
12/19/2022
Inducing Character-level Structure in Subword-based Language Models with Type-level Interchange Intervention Training
Language tasks involving character-level manipulations (e.g., spelling c...
share
research
∙
06/06/2021
Causal Abstractions of Neural Networks
Structural analysis methods (e.g., probing and feature attribution) are ...
research
∙
04/17/2021
Decrypting Cryptic Crosswords: Semantically Complex Wordplay Puzzles as a Target for NLP
Cryptic crosswords, the dominant English-language crossword variety in t...
research
∙
04/16/2021
Concadia: Tackling image accessibility with context
Images have become an integral part of online media. This has enhanced s...
research
∙
01/02/2021
Baleen: Robust Multi-Hop Reasoning at Scale via Condensed Retrieval
Multi-hop reasoning (i.e., reasoning across two or more documents) at sc...
research
∙
05/23/2015
