Papers by Carlotta Domeniconi
Enhancing Out-of-Vocabulary Estimation with Subword Attention (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to learn OOV word representations use advanced architectures like attention on the context of the word, but they tend to use simple structures like ngram addition or character based convolutional neural networks (CNN) |
| Approach: | They propose a transformer-based OOV estimation model that uses attention mechanisms on both the context and the subwords to learn OOV representations. |
| Outcome: | The proposed model outperforms current state-of-the-art models on OOV representations based on attention mechanisms on the context and subwords . |
Beyond Bias Scores: Unmasking Vacuous Neutrality in Small Language Models (2026.eacl-srw)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are expensive to deploy locally and can reproduce harmful social biases in high-stakes settings such as healthcare and education. |
| Approach: | They propose a multi-dimensional evaluation paradigm to assess SLM fairness prior to deployment. |
| Outcome: | The proposed framework examines model robustness across four stages - biases, utility, ambiguity handling, and positional bias over diverse social bias categories. |
Subword Attention and Post-Processing for Rare and Unknown Contextualized Embeddings (2024.findings-naacl)
Copied to clipboard
| Challenge: | Word embeddings are useful, but struggle on rare and unknown words. |
| Approach: | They propose a rare/unknown embedding architecture that focuses on contextualized representations. |
| Outcome: | The proposed architecture improves performance in most intrinsic and downstream tasks. |