Papers › Applying a Pre-trained Language Model to Spanish Twitter Humor Prediction

Applying a Pre-trained Language Model to Spanish Twitter Humor Prediction

6 Jul 2019arXiv:1907.03187archive 2025-07-28

Bobak Farzin, Piotr Czapla, Jeremy Howard

Our entry into the HAHA 2019 Challenge placed 3ʳᵈ in the classification task and 2ⁿᵈ in the regression task. We describe our system and innovations, as well as comparing our results to a Naive Bayes baseline. A large Twitter based corpus allowed us to train a language model from scratch focused on Spanish and transfer that knowledge to our competition model. To overcome the inherent errors in some labels we reduce our class confidence with label smoothing in the loss function. All the code for our project is included in a GitHub repository for easy reference and to enable replication by others.

PaperPDFCode

Code

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Language ModelingLanguage Modellingregression

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Label Smoothing

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections