Papers by Lis Pereira

4 papers
QA-based Event Start-Points Ordering for Clinical Temporal Relation Annotation (2024.lrec-main)

Copied to clipboard

Challenge: Temporal relation annotation in the clinical domain is crucial but challenging due to its workload and the medical expertise required.
Approach: They propose an annotation method that integrates event start-points ordering and question-answering as the annotation format.
Outcome: The proposed method achieves a 0.72 F1 score and enables collaboration among medical experts and non-experts.
AMR-RE: Abstract Meaning Representations for Retrieval-Based In-Context Learning in Relation Extraction (2025.naacl-srw)

Copied to clipboard

Challenge: Existing in-context learning methods for relation extraction often overlook entity relationships . Existing methods for RE prioritize language similarity over structural similarity .
Approach: They propose an AMR-enhanced retrieval-based ICL method for relation extraction . their method retrieves in-context examples based on semantic structure similarity .
Outcome: The proposed method outperforms baselines on four English RE datasets and in the more demanding unsupervised setting.
Posterior Differential Regularization with f-divergence for Improving Model Robustness (2021.naacl-main)

Copied to clipboard

Challenge: Recent studies show that pre-trained models suffer catastrophic degradation in out-of-domain generalization to datasets with domain shift or adversarial scenarios.
Approach: They propose to regularize the posterior difference between clean and noisy inputs by using a Jacobian regularization framework and a virtual adversarial training framework.
Outcome: The proposed framework can improve model robustness in fully supervised and semi-supervised settings.
Targeted Adversarial Training for Natural Language Understanding (2021.naacl-main)

Copied to clipboard

Challenge: Existing adversarial training approaches focus on making adversarials less expensive or regularizing rather than replacing the standard training objective.
Approach: They propose an algorithm to introspect current mistakes and prioritize adversarial training steps to where the model errs the most.
Outcome: The proposed algorithm improves adversarial training for natural language understanding by introspecting mistakes and prioritizing training steps to where the model errs the most.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations