Adding a similar/2 predicate over pretrained embeddings and fine-tuning those embeddings with a Logic Tensor Network improves TILDE F1 on hate speech, spam, and drug response tasks.
https://huggingface.co/fse/glove-twitter-200 (2023), accessed: 2025-05-28
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Enhancing Symbolic Machine Learning by Subsymbolic Representations
Adding a similar/2 predicate over pretrained embeddings and fine-tuning those embeddings with a Logic Tensor Network improves TILDE F1 on hate speech, spam, and drug response tasks.