Unsupervised Domain Adaptation for Event Detection using Domain-specific Adapters

no code implementations • Findings (ACL) 2021 • Nghia Ngo Trung, Duy Phung, Thien Huu Nguyen

Event Detection Unsupervised Domain Adaptation

Modeling Document-Level Context for Event Detection via Important Context Selection

no code implementations • EMNLP 2021 • Amir Pouran Ben Veyseh, Minh Van Nguyen, Nghia Ngo Trung, Bonan Min, Thien Huu Nguyen

To address this issue, we propose a novel method to model document-level context for ED that dynamically selects relevant sentences in the document for the event prediction of the target sentence.

Event Detection Representation Learning +2

Unsupervised Domain Adaptation for Text Classification via Meta Self-Paced Learning

no code implementations • COLING 2022 • Nghia Ngo Trung, Linh Ngo Van, Thien Huu Nguyen

A shift in data distribution can have a significant impact on performance of a text classification model.

Meta-Learning text-classification +2

Selecting Optimal Context Sentences for Event-Event Relation Extraction

1 code implementation • AAAI 2022 • Hieu Man Duc Trong, Nghia Ngo Trung, Linh Van Ngo, and Thien Huu Nguyen

To achieve this goal, our work addresses the problems of subevent relation extraction (SRE) and temporal event relation extraction (TRE) that aim to predict subevent and temporal relations between two given event mentions/triggers in texts.

Event Relation Extraction Relation +2