970 B

Raw Blame History

ANLP_WS24_CA2

Master MDS Use NLP techniques to analyse texts or to build an application. Document your approach.

TODOS

data

maybe buffer zone between good and bad jokes (trade off would be less data)
maybe not bineary classification
maybe change to humor detection (more data available)
dataset shape doesnt work correctly
history: integrate validation loss

Data

https://competitions.codalab.org/competitions/27446

https://aclanthology.org/2021.semeval-1.9.pdf#:~:text=HaHackathon%20is%20the%20first%20shared%20task%20to%20combine,its%20average%20ratings%20for%20both%20humor%20and%20offense.

Hackathon: https://homepages.inf.ed.ac.uk/s1573290/data.html

Data embeddings

gloVe 6B tokens: https://nlp.stanford.edu/projects/glove/

Not Prioritised (Pun data)

Challenge https://alt.qcri.org/semeval2017/task7/
Pun Annotated Amazon (joke not included ...): https://github.com/amazon-science/expunations/tree/main/data