7 citations · 38 across the 20 of their papers we have counts for
20 papers
FACTUAL: A Benchmark for Faithful and Consistent Textual Scene Graph Parsing
Zhuang Li, Yuyang Chai, Terry Yue Zhuo +5
Textual scene graph parsing has become increasingly important in various vision-language applications, including image caption evaluation and image retrieval. However, existing sce…
Generating Adversarial Examples with Task Oriented Multi-Objective Optimization
Anh Bui, Trung Le, He Zhao +3
Deep learning models, even the-state-of-the-art ones, are highly vulnerable to adversarial examples. Adversarial training is one of the most efficient methods to improve the model'…
Class based Influence Functions for Error Detection
Thang Nguyen-Duc, Hoang Thanh-Tung, Quan Hung Tran +4
Influence functions (IFs) are a powerful tool for detecting anomalous examples in large scale datasets. However, they are unstable when applied to deep networks. In this paper, we…
Vision Transformer Visualization: What Neurons Tell and How Neurons Behave?
Van-Anh Nguyen, Khanh Pham Dinh, Long Tung Vuong +4
Recently vision transformers (ViT) have been applied successfully for various tasks in computer vision. However, important questions such as why they work or how they behave still…
An Additive Instance-Wise Approach to Multi-class Model Interpretation
Vy Vo, Van Nguyen, Trung Le +4
Interpretable machine learning offers insights into what factors drive a certain prediction of a black-box system. A large number of interpreting methods focus on identifying expla…
A Unified Wasserstein Distributional Robustness Framework for Adversarial Training
Tuan Anh Bui, Trung Le, Quan Tran +2
It is well-known that deep neural networks (DNNs) are susceptible to adversarial attacks, exposing a severe fragility of deep learning systems. As the result, adversarial training…
ReGVD: Revisiting Graph Neural Networks for Vulnerability Detection
Van-Anh Nguyen, Dai Quoc Nguyen, Van Nguyen +3
Identifying vulnerabilities in the source code is essential to protect the software systems from cyber security attacks. It, however, is also a challenging step that requires speci…
Few-Shot Intent Detection via Contrastive Pre-Training and Fine-Tuning
Jianguo Zhang, Trung Bui, Seunghyun Yoon +6
In this work, we focus on a more challenging few-shot intent detection scenario where many intents are fine-grained and semantically similar. We present a simple yet effective few-…
Joint Biomedical Entity and Relation Extraction with Knowledge-Enhanced Collective Inference
Tuan Lai, Heng Ji, ChengXiang Zhai +1
Compared to the general news domain, information extraction (IE) from biomedical text requires much broader domain knowledge. However, many previous IE methods do not utilize any e…
A Context-Dependent Gated Module for Incorporating Symbolic Semantics into Event Coreference Resolution
Tuan Lai, Heng Ji, Trung Bui +3
Event coreference resolution is an important research problem with many applications. Despite the recent remarkable success of pretrained language models, we argue that it is still…
Explain by Evidence: An Explainable Memory-based Neural Network for Question Answering
Quan Tran, Nhan Dam, Tuan Lai +4
Interpretability and explainability of deep neural networks are challenging due to their scale, complexity, and the agreeable notions on which the explaining process rests. Previou…
What Does This Acronym Mean? Introducing a New Dataset for Acronym Identification and Disambiguation
Amir Pouran Ben Veyseh, Franck Dernoncourt, Quan Hung Tran +1
Acronyms are the short forms of phrases that facilitate conveying lengthy sentences in documents and serve as one of the mainstays of writing. Due to their importance, identifying…
Improving Aspect-based Sentiment Analysis with Gated Graph Convolutional Networks and Syntax-based Regulation
Amir Pouran Ben Veyseh, Nasim Nour, Franck Dernoncourt +3
Aspect-based Sentiment Analysis (ABSA) seeks to predict the sentiment polarity of a sentence toward a specific aspect. Recently, it has been shown that dependency trees can be inte…
A Joint Learning Approach based on Self-Distillation for Keyphrase Extraction from Scientific Documents
Tuan Manh Lai, Trung Bui, Doo Soon Kim +1
Keyphrase extraction is the task of extracting a small set of phrases that best describe a document. Most existing benchmark datasets for the task typically have limited numbers of…
Scene Graph Modification Based on Natural Language Commands
Xuanli He, Quan Hung Tran, Gholamreza Haffari +5
Structured representations like graphs and parse trees play a crucial role in many Natural Language Processing systems. In recent years, the advancements in multi-turn user interfa…
Open-Edit: Open-Domain Image Manipulation with Open-Vocabulary Instructions
Xihui Liu, Zhe Lin, Jianming Zhang +4
We propose a novel algorithm, named Open-Edit, which is the first attempt on open-domain image manipulation with open-vocabulary instructions. It is a challenging task considering…
Context-Aware Group Captioning via Self-Attention and Contrastive Features
Zhuowan Li, Quan Tran, Long Mai +2
While image captioning has progressed rapidly, existing works focus mainly on describing single images. In this paper, we introduce a new task, context-aware group captioning, whic…
A Simple but Effective BERT Model for Dialog State Tracking on Resource-Limited Systems
Tuan Manh Lai, Quan Hung Tran, Trung Bui +1
In a task-oriented dialog system, the goal of dialog state tracking (DST) is to monitor the state of the conversation from the dialog history. Recently, many deep learning based me…
A Gated Self-attention Memory Network for Answer Selection
Tuan Lai, Quan Hung Tran, Trung Bui +1
Answer selection is an important research problem, with applications in many areas. Previous deep learning based approaches for the task mainly adopt the Compare-Aggregate architec…
Exploring Textual and Speech information in Dialogue Act Classification with Speaker Domain Adaptation
Xuanli He, Quan Hung Tran, William Havard +3
In spite of the recent success of Dialogue Act (DA) classification, the majority of prior works focus on text-based classification with oracle transcriptions, i.e. human transcript…