Unleash GPT-2 power for event detection

APB Veyseh, V Lai, F Dernoncourt… - Proceedings of the 59th …, 2021 - aclanthology.org
Event Detection (ED) aims to recognize mentions of events (ie, event triggers) and their
types in text. Recently, several ED datasets in various domains have been proposed …

Trigger is not sufficient: Exploiting frame-aware knowledge for implicit event argument extraction

K Wei, X Sun, Z Zhang, J Zhang, G Zhi… - Proceedings of the 59th …, 2021 - aclanthology.org
Abstract Implicit Event Argument Extraction seeks to identify arguments that play direct or
implicit roles in a given event. However, most prior works focus on capturing direct relations …

What the role is vs. what plays the role: Semi-supervised event argument extraction via dual question answering

Y Zhou, Y Chen, J Zhao, Y Wu, J Xu, J Li - Proceedings of the AAAI …, 2021 - ojs.aaai.org
Event argument extraction is an essential task in event extraction, and become particularly
challenging in the case of low-resource scenarios. We solve the issues in existing studies …

Graph transformer networks with syntactic and semantic structures for event argument extraction

APB Veyseh, TN Nguyen, TH Nguyen - arXiv preprint arXiv:2010.13391, 2020 - arxiv.org
The goal of Event Argument Extraction (EAE) is to find the role of each entity mention for a
given event trigger word. It has been shown in the previous works that the syntactic …

Cross-lingual event detection via optimized adversarial training

LG Nateras, M Van Nguyen… - Proceedings of the 2022 …, 2022 - aclanthology.org
In this work, we focus on Cross-Lingual Event Detection where a model is trained on data
from a source language but its performance is evaluated on data from a second, target …

Modeling document-level context for event detection via important context selection

APB Veyseh, M Van Nguyen, NN Trung… - Proceedings of the …, 2021 - aclanthology.org
Abstract The task of Event Detection (ED) in Information Extraction aims to recognize and
classify trigger words of events in text. The recent progress has featured advanced …

Resource-enhanced neural model for event argument extraction

J Ma, S Wang, R Anubhai, M Ballesteros… - arXiv preprint arXiv …, 2020 - arxiv.org
Event argument extraction (EAE) aims to identify the arguments of an event and classify the
roles that those arguments play. Despite great efforts made in prior work, there remain many …

Document-level event argument extraction via optimal transport

APB Veyseh, M Van Nguyen… - Findings of the …, 2022 - aclanthology.org
Abstract 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 …

Aspect-level information discrepancies across heterogeneous vulnerability reports: Severity, types and detection methods

J Sun, Z Xing, X Xia, Q Lu, X Xu, L Zhu - ACM Transactions on Software …, 2023 - dl.acm.org
Vulnerable third-party libraries pose significant threats to software applications that reuse
these libraries. At an industry scale of reuse, manual analysis of third-party library …

Implicit event argument extraction with argument-argument relational knowledge

K Wei, X Sun, Z Zhang, L Jin, J Zhang… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
As a challenging sub-task of event argument extraction, implicit event argument extraction
seeks to identify document-level arguments that play direct or implicit roles in a given event …