Introduces a controlled toxicity decoding method that generates diverse interpretations of out-of-context sentences aligned with human judgments in syntax and semantics.
In Pro- ceedings of the 2021 Conference of the North Amer- ican Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 3511–3535, Online
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Mimicking How Humans Interpret Out-of-Context Sentences Through Controlled Toxicity Decoding
Introduces a controlled toxicity decoding method that generates diverse interpretations of out-of-context sentences aligned with human judgments in syntax and semantics.