Papers by Thi-Nhung Nguyen
BKEE: Pioneering Event Extraction in the Vietnamese Language (2024.lrec-main)
Copied to clipboard
| Challenge: | Event Extraction (EE) is a fundamental task in information extraction. |
| Approach: | They propose a Vietnamese event extraction dataset that includes 33 different event types and 28 different event argument roles. |
| Outcome: | The proposed dataset provides a labeled dataset for entity mentions, event mentions and event arguments on 1066 documents. |
An Uncertainty-Aware Encoder for Aspect Detection (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for aspect detection use seed words as priors or features of topic models. |
| Approach: | They propose a weakly-supervised method to exploit seed words for aspect detection . goal is approximating similarity between segments and aspects and ground-truth similarity generated from seed words. |
| Outcome: | The proposed method outperforms previous work on several benchmarks in various domains. |
SharpSeq: Empowering Continual Event Detection through Sharpness-Aware Sequential-task Learning (2024.naacl-long)
Copied to clipboard
| Challenge: | Existing methods for continual event detection suffer from catastrophic forgetting . a novel continual learning paradigm leveraging sharpness-aware minimization is needed . |
| Approach: | They propose a continual learning paradigm that leverages sharpness-aware minimization and a generative model to balance training data distribution. |
| Outcome: | The proposed approach outperforms existing methods on real-world datasets. |
A Self-enhancement Multitask Framework for Unsupervised Aspect Category Detection (2023.emnlp-main)
Copied to clipboard
| Challenge: | Recent work has focused on learning embedding spaces for seed words and sentences to establish similarities between sentences and aspects. |
| Approach: | They propose a framework that enhances the quality of initial seed words and selects high-quality sentences instead of using the entire dataset. |
| Outcome: | The proposed framework surpasses strong baselines on standard datasets and improves on the noise resolution task. |