Thien Nguyen


2022

pdf bib
Transfer Learning and Prediction Consistency for Detecting Offensive Spans of Text
Amir Pouran Ben Veyseh | Ning Xu | Quan Tran | Varun Manjunatha | Franck Dernoncourt | Thien Nguyen
Findings of the Association for Computational Linguistics: ACL 2022

Toxic span detection is the task of recognizing offensive spans in a text snippet. Although there has been prior work on classifying text snippets as offensive or not, the task of recognizing spans responsible for the toxicity of a text is not explored yet. In this work, we introduce a novel multi-task framework for toxic span detection in which the model seeks to simultaneously predict offensive words and opinion phrases to leverage their inter-dependencies and improve the performance. Moreover, we introduce a novel regularization mechanism to encourage the consistency of the model predictions across similar inputs for toxic span detection. Our extensive experiments demonstrate the effectiveness of the proposed model compared to strong baselines.

pdf bib
Document-Level Event Argument Extraction via Optimal Transport
Amir Pouran Ben Veyseh | Minh Van Nguyen | Franck Dernoncourt | Bonan Min | Thien Nguyen
Findings of the Association for Computational Linguistics: ACL 2022

Event Argument Extraction (EAE) is one of the sub-tasks of event extraction, aiming to recognize the role of each entity mention toward a specific event trigger. Despite the success of prior works in sentence-level EAE, the document-level setting is less explored. In particular, whereas syntactic structures of sentences have been shown to be effective for sentence-level EAE, prior document-level EAE models totally ignore syntactic structures for documents. Hence, in this work, we study the importance of syntactic structures in document-level EAE. Specifically, we propose to employ Optimal Transport (OT) to induce structures of documents based on sentence-level syntactic structures and tailored to EAE task. Furthermore, we propose a novel regularization technique to explicitly constrain the contributions of unrelated context words in the final prediction for EAE. We perform extensive experiments on the benchmark document-level EAE dataset RAMS that leads to the state-of-the-art performance. Moreover, our experiments on the ACE 2005 dataset reveals the effectiveness of the proposed model in the sentence-level EAE by establishing new state-of-the-art results.

2019

pdf bib
Extending Event Detection to New Types with Learning from Keywords
Viet Dac Lai | Thien Nguyen
Proceedings of the 5th Workshop on Noisy User-generated Text (W-NUT 2019)

Traditional event detection classifies a word or a phrase in a given sentence for a set of prede- fined event types. The limitation of such pre- defined set is that it prevents the adaptation of the event detection models to new event types. We study a novel formulation of event detec- tion that describes types via several keywords to match the contexts in documents. This fa- cilitates the operation of the models to new types. We introduce a novel feature-based attention mechanism for convolutional neural networks for event detection in the new for- mulation. Our extensive experiments demon- strate the benefits of the new formulation for new type extension for event detection as well as the proposed attention mechanism for this problem

2006

pdf bib
Ontology-Based Natural Language Query Processing for the Biological Domain
Jisheng Liang | Thien Nguyen | Krzysztof Koperski | Giovanni Marchisio
Proceedings of the HLT-NAACL BioNLP Workshop on Linking Natural Language and Biology