Event Extraction (EE) is a fundamental task in information extraction, aimed at identifying events and their associated arguments within textual data. It holds significant importance in various applications and serves as a catalyst for the development of related tasks. Despite the availability of numerous datasets and methods for event extraction in various languages, there has been a notable absence of a dedicated dataset for the Vietnamese language. To address this limitation, we propose BKEE, a novel event extraction dataset for Vietnamese. BKEE encompasses over 33 distinct event types and 28 different event argument roles, providing a labeled dataset for entity mentions, event mentions, and event arguments on 1066 documents. Additionally, we establish robust baselines for potential downstream tasks on this dataset, facilitating the analysis of challenges and future development prospects in the field of Vietnamese event extraction.

Thanh-Thien Le, Viet Dao, Linh Nguyen, Thi-Nhung Nguyen, Linh Ngo, Thien Nguyen. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2024.

Our work addresses the problem of unsupervised Aspect Category Detection using a small set of seed words.Recent works have focused on learning embedding spaces for seed words and sentences to establish similarities between sentences and aspects.However, aspect representations are limited by the quality of initial seed words, and model performances are compromised by noise.To mitigate this limitation, we propose a simple framework that automatically enhances the quality of initial seed words and selects high-quality sentences for training instead of using the entire dataset.Our main concepts are to add a number of seed words to the initial set and to treat the task of noise resolution as a task of augmenting data for a low-resource task.In addition, we jointly train Aspect Category Detection with Aspect Term Extraction and Aspect Term Polarity to further enhance performance.This approach facilitates shared representation learning, allowing Aspect Category Detection to benefit from the additional guidance offered by other tasks.Extensive experiments demonstrate that our framework surpasses strong baselines on standard datasets.