Papers by Alexander Ororbia
Disagreement Matters: Preserving Label Diversity by Jointly Modeling Item and Annotator Label Distributions with DisCo (2023.findings-acl)
Copied to clipboard
Tharindu Cyril Weerasooriya, Alexander Ororbia, Raj Bhensadadia, Ashiqur KhudaBukhsh, Christopher Homan
| Challenge: | a recent study shows that annotator disagreement is common in supervised learning . a simple neural model that learns to predict annotators' labels is competitive with other models that do not model specific annotations. |
| Approach: | They propose a neural model that learns to predict annotator distributions by aggregating over all annotators. |
| Outcome: | The proposed model outperforms models that do not model specific annotators or do not learn label distribution learning. |
Like a Baby: Visually Situated Neural Language Acquisition (P19-1)
Copied to clipboard
| Challenge: | A multi-modal neural architecture outperforms its equivalent trained on language alone with a 2% decrease in perplexity . |
| Approach: | They propose to use visual context to train neural language models to perform next-word prediction. |
| Outcome: | The proposed model outperforms its equivalent trained on language with 2% decrease in perplexity even when no visual context is available at test. |
fBERT: A Neural Transformer for Identifying Offensive Content (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing models such as BERT, XLNET, and XLM-R have outperformed other neural architectures and statistical learning methods in the identification of offensive language and hate speech. |
| Approach: | They present a BERT model retrained on SOLID, the largest English offensive language identification corpus available with over 1.4 million offensive instances. |
| Outcome: | The proposed model outperforms models trained on SOLID, the largest English offensive language identification corpus available with over 1.4 million offensive instances. |