Papers by Josip Jukić
On Dataset Transferability in Active Learning for Transformers (2023.findings-acl)
Copied to clipboard
| Challenge: | Active learning (AL) aims to reduce labeling costs by querying the examples most beneficial for model learning. |
| Approach: | They propose to query examples most beneficial for model learning by querying data points most informative for labeling. |
| Outcome: | The proposed method reduces labeling costs by querying the examples most beneficial for model learning. |
Easy to Decide, Hard to Agree: Reducing Disagreements Between Saliency Methods (2023.findings-acl)
Copied to clipboard
| Challenge: | A popular approach to unveiling the black box of neural NLP models is to leverage saliency methods, which assign scalar importance scores to each input component. |
| Approach: | They propose to use saliency methods to evaluate whether an explanation is faithful and argue that Pearson-r is a better-suited alternative to rank correlation. |
| Outcome: | The proposed methods exhibit weak rank correlations even when applied to the same model instance and advocated for alternative diagnostic methods. |
You Are What You Talk About: Inducing Evaluative Topics for Personality Analysis (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Recent studies have focused on the relationship between personality and evaluative language. |
| Approach: | They propose to map evaluative topics to pre-filtered evalative text and link evalueative topics with individual text authors to build their ev emvaluative profiles. |
| Outcome: | The proposed approach is validated by observing correlations consistent with prior research in personality psychology. |
Parameter-Efficient Language Model Tuning with Active Learning in Low-Resource Settings (2023.emnlp-main)
Copied to clipboard
| Challenge: | Pre-trained language models (PLMs) have ignited a surge in demand for effective fine-tuning techniques . data labeling is notoriously time-consuming and expensive, hindering the development of sizable labeled datasets . |
| Approach: | They propose to use active learning to reduce labeling costs by minimizing label complexity . they find PEFT adapter modules have significant potential in low-resource settings . |
| Outcome: | The proposed model outperforms FFT in low-resource settings and shows that it yields more stable representations of early and middle layers than FFT. |
ALANNO: An Active Learning Annotation System for Mortals (2023.eacl-demo)
Copied to clipboard
| Challenge: | Active learning (AL) is a special family of machine learning algorithms designed to reduce labeling costs and improve accuracy. |
| Approach: | They developed an open-source annotation system for NLP tasks equipped with features to make AL effective in real-world annotation projects. |
| Outcome: | ALANNO is an open-source annotation system for NLP tasks equipped with features to make AL effective in real-world annotation projects. |