Hiếu Mẫn

Also published as: Hieu Man


Multilingual SubEvent Relation Extraction: A Novel Dataset and Structure Induction Method
Viet Lai | Hieu Man | Linh Ngo | Franck Dernoncourt | Thien Nguyen
Findings of the Association for Computational Linguistics: EMNLP 2022

Subevent Relation Extraction (SRE) is a task in Information Extraction that aims to recognize spatial and temporal containment relations between event mentions in text. Recent methods have utilized pre-trained language models to represent input texts for SRE. However, a key issue in existing SRE methods is the employment of sequential order of words in texts to feed into representation learning methods, thus unable to explicitly focus on important context words and their interactions to enhance representations. In this work, we introduce a new method for SRE that learns to induce effective graph structures for input texts to boost representation learning. Our method features a word alignment framework with dependency paths and optimal transport to identify important context words to form effective graph structures for SRE. In addition, to enable SRE research on non-English languages, we present a new multilingual SRE dataset for five typologically different languages. Extensive experiments reveal the state-of-the-art performance for our method on different datasets and languages.

Event Causality Identification via Generation of Important Context Words
Hieu Man | Minh Nguyen | Thien Nguyen
Proceedings of the 11th Joint Conference on Lexical and Computational Semantics

An important problem of Information Extraction involves Event Causality Identification (ECI) that seeks to identify causal relation between pairs of event mentions. Prior models for ECI have mainly solved the problem using the classification framework that does not explore prediction/generation of important context words from input sentences for causal recognition. In this work, we consider the words along the dependency path between the two event mentions in the dependency tree as the important context words for ECI. We introduce dependency path generation as a complementary task for ECI, which can be solved jointly with causal label prediction to improve the performance. To facilitate the multi-task learning, we cast ECI into a generation problem that aims to generate both causal relation and dependency path words from input sentence. In addition, we propose to use the REINFORCE algorithm to train our generative model where novel reward functions are designed to capture both causal prediction accuracy and generation quality. The experiments on two benchmark datasets demonstrate state-of-the-art performance of the proposed model for ECI.


Vietnamese Relation Extraction with BERT-based Models at VLSP 2020
Thuật Nguyễn | Hiếu Mẫn
Proceedings of the 7th International Workshop on Vietnamese Language and Speech Processing