no code implementations • NAACL (ACL) 2022 • David Fraile Navarro, Mark Dras, Shlomo Berkovsky
Abstractive summarization of medical dialogues presents a challenge for standard training approaches, given the paucity of suitable datasets.
no code implementations • 29 Feb 2024 • Ansh Arora, Xuanli He, Maximilian Mozes, Srinibas Swain, Mark Dras, Qiongkai Xu
The democratization of pre-trained language models through open-source initiatives has rapidly advanced innovation and expanded access to cutting-edge technologies.
2 code implementations • 19 Sep 2023 • Shakila Mahjabin Tonni, Mark Dras
Adversarial examples, deliberately crafted using small perturbations to fool deep neural networks, were first studied in image processing and more recently in NLP.
1 code implementation • 22 Jun 2023 • Haolong Xiang, Xuyun Zhang, Hongsheng Hu, Lianyong Qi, Wanchun Dou, Mark Dras, Amin Beheshti, Xiaolong Xu
Extensive experiments on a series of benchmarking datasets for comparative and ablation studies demonstrate that our approach can efficiently and robustly achieve better detection performance in general than the state-of-the-arts including the deep learning based methods.
no code implementations • 9 Nov 2022 • Pedro Faustini, Natasha Fernandes, Shakila Tonni, Annabelle McIver, Mark Dras
In this paper, we apply \textit{directional privacy}, via a mechanism based on the von Mises-Fisher (VMF) distribution, to perturb gradients in terms of \textit{angular distance} so that gradient direction is broadly preserved.
1 code implementation • RepL4NLP (ACL) 2022 • Na Liu, Mark Dras, Wei Emma Zhang
Although deep neural networks have achieved state-of-the-art performance in various machine learning tasks, adversarial examples, constructed by adding small non-random perturbations to correctly classified inputs, successfully fool highly expressive deep classifiers into incorrect predictions.
no code implementations • 18 Mar 2022 • Xusheng Zhao, Jia Wu, Hao Peng, Amin Beheshti, Jessica J. M. Monaghan, David Mcalpine, Heivet Hernandez-Perez, Mark Dras, Qiong Dai, Yangyang Li, Philip S. Yu, Lifang He
Modern neuroimaging techniques, such as diffusion tensor imaging (DTI) and functional magnetic resonance imaging (fMRI), enable us to model the human brain as a brain network or connectome.
1 code implementation • ACL 2021 • YuFei Wang, Ian Wood, Stephen Wan, Mark Dras, Mark Johnson
In this paper, we propose Mention Flags (MF), which traces whether lexical constraints are satisfied in the generated outputs in an S2S decoder.
no code implementations • NeurIPS 2021 • YuFei Wang, Can Xu, Huang Hu, Chongyang Tao, Stephen Wan, Mark Dras, Mark Johnson, Daxin Jiang
Sequence-to-Sequence (S2S) neural text generation models, especially the pre-trained ones (e. g., BART and T5), have exhibited compelling performance on various natural language generation tasks.
no code implementations • Joint Conference on Lexical and Computational Semantics 2020 • Chakaveh Saedi, Mark Dras
Author obfuscation is the task of masking the author of a piece of text, with applications in privacy.
1 code implementation • 5 Jun 2020 • Omid Mohamad Nezami, Akshay Chaturvedi, Mark Dras, Utpal Garain
We specifically aim to attack the widely used Faster R-CNN by changing the predicted label for a particular object in an image: where prior work has targeted one specific object (a stop sign), we generalise to arbitrary objects, with the key challenge being the need to change the labels of all bounding boxes for all instances of that object type.
no code implementations • 23 Dec 2019 • Chakaveh Saedi, Mark Dras
Authorship attribution is the process of identifying the author of a text.
no code implementations • 8 Aug 2019 • Omid Mohamad Nezami, Mark Dras, Stephen Wan, Cecile Paris
An analysis of the generated captions finds that, perhaps unexpectedly, the improvement in caption quality appears to come not from the addition of adjectives linked to emotional aspects of the images, but from more variety in the actions described in the captions.
no code implementations • 8 Aug 2019 • Omid Mohamad Nezami, Mark Dras, Stephen Wan, Cecile Paris, Len Hamey
While most image captioning aims to generate objective descriptions of images, the last few years have seen work on generating visually grounded image captions which have a specific style (e. g., incorporating positive or negative sentiment).
no code implementations • 26 Nov 2018 • Natasha Fernandes, Mark Dras, Annabelle McIver
We address the problem of how to "obfuscate" texts by removing stylistic clues which can identify authorship, whilst preserving (as much as possible) the content of the text.
no code implementations • 24 Nov 2018 • Omid Mohamad Nezami, Mark Dras, Stephen Wan, Cecile Paris
However, such models typically have difficulty in balancing the semantic aspects of the image and the non-factual dimensions of the caption; in addition, it can be observed that humans may focus on different aspects of an image depending on the chosen sentiment or style of the caption.
no code implementations • CL 2018 • Shervin Malmasi, Mark Dras
Ensemble methods using multiple classifiers have proven to be among the most successful approaches for the task of Native Language Identification (NLI), achieving the current state of the art.
3 code implementations • 7 Aug 2018 • Omid Mohamad Nezami, Mark Dras, Len Hamey, Deborah Richards, Stephen Wan, Cecile Paris
This paper presents a deep learning model to improve engagement recognition from images that overcomes the data sparsity challenge by pre-training on readily available basic facial expression data, before training on specialised engagement data.
Facial Expression Recognition Facial Expression Recognition (FER)
1 code implementation • 6 Jul 2018 • Omid Mohamad Nezami, Mark Dras, Peter Anderson, Len Hamey
In this work, we present two variants of our Face-Cap model, which embed facial expression features in different ways, to generate image captions.
no code implementations • ACL 2018 • Mark Johnson, Peter Anderson, Mark Dras, Mark Steedman
Because obtaining training data is often the most difficult part of an NLP or ML project, we develop methods for predicting how much data is required to achieve a desired test accuracy by extrapolating results from models trained on a small pilot training dataset.
no code implementations • 22 May 2018 • Natasha Fernandes, Mark Dras, Annabelle McIver
The problem of obfuscating the authorship of a text document has received little attention in the literature to date.
Cryptography and Security
2 code implementations • NAACL 2018 • Thanh Vu, Dat Quoc Nguyen, Dai Quoc Nguyen, Mark Dras, Mark Johnson
We present an easy-to-use and fast toolkit, namely VnCoreNLP---a Java NLP annotation pipeline for Vietnamese.
1 code implementation • ALTA 2017 • Dat Quoc Nguyen, Thanh Vu, Dai Quoc Nguyen, Mark Dras, Mark Johnson
This paper presents an empirical comparison of two strategies for Vietnamese Part-of-Speech (POS) tagging from unsegmented text: (i) a pipeline strategy where we consider the output of a word segmenter as the input of a POS tagger, and (ii) a joint strategy where we predict a combined segmentation and POS tag for each syllable.
1 code implementation • LREC 2018 • Dat Quoc Nguyen, Dai Quoc Nguyen, Thanh Vu, Mark Dras, Mark Johnson
We propose a novel approach to Vietnamese word segmentation.
no code implementations • ACL 2017 • Shervin Malmasi, Mark Dras
We evaluate feature hashing for language identification (LID), a method not previously used for this task.
no code implementations • ACL 2017 • Shervin Malmasi, Mark Dras, Mark Johnson, Lan Du, Magdalena Wolska
Most work on segmenting text does so on the basis of topic changes, but it can be of interest to segment by other, stylistically expressed characteristics such as change of authorship or native language.
1 code implementation • CONLL 2017 • Dat Quoc Nguyen, Mark Dras, Mark Johnson
We present a novel neural network model that learns POS tagging and graph-based dependency parsing jointly.
Ranked #5 on Part-Of-Speech Tagging on UD
no code implementations • 19 Mar 2017 • Shervin Malmasi, Mark Dras
Ensemble methods using multiple classifiers have proven to be the most successful approach for the task of Native Language Identification (NLI), achieving the current state of the art.
no code implementations • ALTA 2016 • Dat Quoc Nguyen, Mark Dras, Mark Johnson
This paper presents an empirical comparison of different dependency parsers for Vietnamese, which has some unusual characteristics such as copula drop and verb serialization.
no code implementations • LREC 2016 • Marcos Zampieri, Shervin Malmasi, Mark Dras
This paper presents a number of experiments to model changes in a historical Portuguese corpus composed of literary texts for the purpose of temporal text classification.
no code implementations • LREC 2012 • Teresa Lynn, {\"O}zlem {\c{C}}etino{\u{g}}lu, Jennifer Foster, Elaine U{\'\i} Dhonnchadha, Mark Dras, Josef van Genabith
This paper describes the early stages in the development of new language resources for Irish ― namely the first Irish dependency treebank and the first Irish statistical dependency parser.