Papers by Vladimir Kniazhevsky
You Told Me That Joke Twice: A Systematic Investigation of Transferability and Robustness of Humor Detection Models (2023.emnlp-main)
Copied to clipboard
| Challenge: | a recent study shows that there is little research on how models trained on humor datasets generalize and behave in the wild. |
| Approach: | They analyze existing English humor datasets and train RoBERTa-based and Nave Bayes classifiers on them. |
| Outcome: | The proposed models show that they can generalize and behave on humor datasets, but the transferability of the models is poor. |