Papers by Jan Snajder
Looking Right is Sometimes Right: Investigating the Capabilities of Decoder-only LLMs for Sequence Labeling (2024.findings-acl)
Copied to clipboard
| Challenge: | Pre-trained language models excel in natural language understanding (NLU) tasks. |
| Approach: | They propose to apply layer-dependent removal of the causal mask (CM) during LLM fine-tuning to improve SL performance. |
| Outcome: | The proposed approach outperforms state-of-the-art SL models on IE tasks, while achieving state- of-the art results is unclear. |
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. |
Leveraging Open Information Extraction for More Robust Domain Transfer of Event Trigger Detection (2024.findings-eacl)
Copied to clipboard
| Challenge: | Event detection is a crucial information extraction task in many domains, such as Wikipedia or news. |
| Approach: | They propose to use subject-object relations obtained from a rule-based open information extraction system to enhance domain transfer of trigger detection (TD) they combine this enhanced transfer with masked language modeling on the target domain, observing further TD transfer gains. |
| Outcome: | The proposed model improves the transfer of triggers between domains and reduces performance drops when using a low-resource source domain to a high-res target domain. |