no code implementations • ALTA 2021 • Narjes Askarian, Ehsan Abbasnejad, Ingrid Zukerman, Wray Buntine, Gholamreza Haffari
In this paper, we propose curriculum-based learning (CL) regime to increase the accuracy of VQA models trained on small datasets.
no code implementations • Findings (EMNLP) 2021 • Fahimeh Saleh, Wray Buntine, Gholamreza Haffari, Lan Du
Multilingual Neural Machine Translation (MNMT) trains a single NMT model that supports translation between multiple languages, rather than training separate models for different languages.
1 code implementation • ACL 2022 • Lan Zhang, Wray Buntine, Ehsan Shareghi
Injecting desired geometric properties into text representations has attracted a lot of attention.
no code implementations • 28 Mar 2024 • Nhu Vo, Dat Quoc Nguyen, Dung D. Le, Massimo Piccardi, Wray Buntine
Machine translation for Vietnamese-English in the medical domain is still an under-explored research area.
no code implementations • 29 Jan 2024 • Weicong Tan, Weiqing Wang, Xin Zhou, Wray Buntine, Gordon Bingham, Hongzhi Yin
Most existing medication recommendation models learn representations for medical concepts based on electronic health records (EHRs) and make recommendations with learnt representations.
no code implementations • 25 Jan 2024 • Jiuzhou Han, Wray Buntine, Ehsan Shareghi
We present the Uncertainty-Aware Language Agent (UALA), a framework that orchestrates the interaction between the agent and the external world using uncertainty quantification.
no code implementations • 15 Jan 2024 • Wei Tan, Ngoc Dang Nguyen, Lan Du, Wray Buntine
Within the scope of natural language processing, the domain of multi-label text classification is uniquely challenging due to its expansive and uneven label distribution.
no code implementations • 15 Dec 2023 • Wei Tan, Lan Du, Wray Buntine
Expected Loss Reduction (ELR) focuses on a Bayesian estimate of the reduction in classification error, and more general costs fit in the same framework.
no code implementations • 23 Nov 2023 • Do Huu Dat, Po Yuan Mao, Tien Hoang Nguyen, Wray Buntine, Mohammed Bennamoun
In our paper, we propose a novel framework that for the first time combines the Modern Hopfield Network with a Mixture of Experts (HOMOE) to classify the compositions of previously unseen objects.
no code implementations • 2 Nov 2023 • Ngoc Dang Nguyen, Wei Tan, Lan Du, Wray Buntine, Richard Beare, Changyou Chen
Named entity recognition (NER), a task that identifies and categorizes named entities such as persons or organizations from text, is traditionally framed as a multi-class classification problem.
1 code implementation • 15 Sep 2023 • Jiuzhou Han, Wray Buntine, Ehsan Shareghi
Semi-structured explanation depicts the implicit process of a reasoner with an explicit representation.
no code implementations • 27 Jun 2023 • Xinzhe Li, Ming Liu, Shang Gao, Wray Buntine
Adversarial robustness, domain generalization and dataset biases are three active lines of research contributing to out-of-distribution (OOD) evaluation on neural NLP models.
1 code implementation • 21 May 2023 • Jiuzhou Han, Nigel Collier, Wray Buntine, Ehsan Shareghi
We show how a small language model could be trained to act as a verifier module for the output of an LLM(i. e., ChatGPT, GPT-4), and to iteratively improve its performance via fine-grained corrective instructions.
no code implementations • 15 Apr 2023 • Jionghao Lin, Wei Tan, Ngoc Dang Nguyen, David Lang, Lan Du, Wray Buntine, Richard Beare, Guanliang Chen, Dragan Gasevic
We note that many prior studies on classifying educational DAs employ cross entropy (CE) loss to optimize DA classifiers on low-resource data with imbalanced DA distribution.
no code implementations • 12 Apr 2023 • Wei Tan, Jionghao Lin, David Lang, Guanliang Chen, Dragan Gasevic, Lan Du, Wray Buntine
Then, the study investigates how the AL methods can select informative samples to support DA classifiers in the AL sampling process.
no code implementations • 9 Dec 2022 • Ngoc Dang Nguyen, Wei Tan, Wray Buntine, Richard Beare, Changyou Chen, Lan Du
To the best of our knowledge, this is the first work that brings AUC maximization to the NER setting.
Low Resource Named Entity Recognition named-entity-recognition +2
1 code implementation • 2 Dec 2022 • Qizhou Wang, Guansong Pang, Mahsa Salehi, Wray Buntine, Christopher Leckie
In doing so, ACT effectively transfers anomaly-informed knowledge from the source graph to learn the complex node relations of the normal class for GAD on the target graph without any specification of the anomaly distributions.
no code implementations • 11 Nov 2022 • Ngoc Dang Nguyen, Lan Du, Wray Buntine, Changyou Chen, Richard Beare
Domain adaptation is an effective solution to data scarcity in low-resource scenarios.
1 code implementation • 10 Jun 2022 • Vy Vo, Weiqing Wang, Wray Buntine
Text simplification is the task of rewriting a text so that it is readable and easily understood.
1 code implementation • NeurIPS 2021 • Wei Tan, Lan Du, Wray Buntine
We convert the ELR framework to estimate the increase in (strictly proper) scores like log probability or negative mean square error, which we call Bayesian Estimate of Mean Proper Scores (BEMPS).
no code implementations • 15 Oct 2021 • Fahimeh Saleh, Wray Buntine, Gholamreza Haffari, Lan Du
Multilingual Neural Machine Translation (MNMT) trains a single NMT model that supports translation between multiple languages, rather than training separate models for different languages.
no code implementations • EMNLP 2021 • Yuan Jin, He Zhao, Ming Liu, Lan Du, Wray Buntine
Neural topic models (NTMs) apply deep neural networks to topic modelling.
no code implementations • Findings (EMNLP) 2021 • Kelvin Lo, Yuan Jin, Weicong Tan, Ming Liu, Lan Du, Wray Buntine
This paper proposes a transformer over transformer framework, called Transformer$^2$, to perform neural text segmentation.
1 code implementation • 14 Oct 2021 • Lan Zhang, Wray Buntine, Ehsan Shareghi
Deep generative models have been widely used in several areas of NLP, and various techniques have been proposed to augment them or address their training challenges.
no code implementations • NAACL 2021 • Caitlin Doogan, Wray Buntine
In this paper, we probe the issue of validity in topic model evaluation and assess how informative coherence measures are for specialized collections used in an applied setting.
1 code implementation • CVPR 2021 • Islam Nassar, Samitha Herath, Ehsan Abbasnejad, Wray Buntine, Gholamreza Haffari
We train two classifiers with two different views of the class labels: one classifier uses the one-hot view of the labels and disregards any potential similarity among the classes, while the other uses a distributed view of the labels and groups potentially similar classes together.
no code implementations • 28 Feb 2021 • He Zhao, Dinh Phung, Viet Huynh, Yuan Jin, Lan Du, Wray Buntine
Topic modelling has been a successful technique for text analysis for almost twenty years.
1 code implementation • 19 Feb 2021 • Dilini Rajapaksha, Chakkrit Tantithamthavorn, Jirayus Jiarpakdee, Christoph Bergmeir, John Grundy, Wray Buntine
Thus, our SQAPlanner paves a way for novel research in actionable software analytics-i. e., generating actionable guidance on what should practitioners do and not do to decrease the risk of having defects to support SQA planning.
no code implementations • 4 Feb 2021 • Bhagya Hettige, Weiqing Wang, Yuan-Fang Li, Suong Le, Wray Buntine
Although a point process (e. g., Hawkes process) is able to model a cascade temporal relationship, it strongly relies on a prior generative process assumption.
no code implementations • 12 Nov 2020 • Yuan Jin, Wray Buntine, Francois Petitjean, Geoffrey I. Webb
For this task, we survey a wide range of techniques available for handling missing values, self-supervised training and pseudo-likelihood training, and adapt them to a suite of algorithms that are suitable for the task.
no code implementations • COLING 2020 • Fahimeh Saleh, Wray Buntine, Gholamreza Haffari
Scarcity of parallel sentence-pairs poses a significant hurdle for training high-quality Neural Machine Translation (NMT) models in bilingually low-resource scenarios.
Knowledge Distillation Low-Resource Neural Machine Translation +4
1 code implementation • ICLR 2021 • He Zhao, Dinh Phung, Viet Huynh, Trung Le, Wray Buntine
Recently, Neural Topic Models (NTMs) inspired by variational autoencoders have obtained increasingly research interest due to their promising results on text analysis.
Ranked #5 on Topic Models on 20NewsGroups
4 code implementations • 14 Jul 2020 • Laurent Valentin Jospin, Wray Buntine, Farid Boussaid, Hamid Laga, Mohammed Bennamoun
Modern deep learning methods constitute incredibly powerful tools to tackle a myriad of challenging problems.
1 code implementation • 8 Dec 2019 • Bhagya Hettige, Yuan-Fang Li, Weiqing Wang, Suong Le, Wray Buntine
To address these limitations, we present $\mathtt{MedGraph}$, a supervised EMR embedding method that captures two types of information: (1) the visit-code associations in an attributed bipartite graph, and (2) the temporal sequencing of visits through a point process.
1 code implementation • 2 Dec 2019 • Bhagya Hettige, Yuan-Fang Li, Weiqing Wang, Wray Buntine
Graph embedding methods transform high-dimensional and complex graph contents into low-dimensional representations.
Ranked #1 on Link Prediction on Pubmed (nonstandard variant)
no code implementations • 11 Aug 2019 • Dilini Rajapaksha, Christoph Bergmeir, Wray Buntine
In this paper, we propose Local Rule-based Model Interpretability with k-optimal Associations (LoRMIkA), a novel model-agnostic approach that obtains k-optimal association rules from a neighbourhood of the instance to be explained.
no code implementations • ACL 2019 • He Zhao, Lan Du, Guanfeng Liu, Wray Buntine
Short texts such as tweets often contain insufficient word co-occurrence information for training conventional topic models.
1 code implementation • 2 May 2019 • He Zhao, Piyush Rai, Lan Du, Wray Buntine, Mingyuan Zhou
Many applications, such as text modelling, high-throughput sequencing, and recommender systems, require analysing sparse, high-dimensional, and overdispersed discrete (count-valued or binary) data.
2 code implementations • NeurIPS 2018 • He Zhao, Lan Du, Wray Buntine, Mingyuan Zhou
Recently, considerable research effort has been devoted to developing deep architectures for topic models to learn topic structures.
no code implementations • CONLL 2018 • Ming Liu, Wray Buntine, Gholamreza Haffari
Traditional active learning (AL) methods for machine translation (MT) rely on heuristics.
1 code implementation • ACL 2018 • Ming Liu, Wray Buntine, Gholamreza Haffari
Heuristic-based active learning (AL) methods are limited when the data distribution of the underlying learning problems vary.
no code implementations • ACL 2018 • Poorya Zaremoodi, Wray Buntine, Gholamreza Haffari
The routing network enables adaptive collaboration by dynamic sharing of blocks conditioned on the task at hand, input, and model state.
1 code implementation • ICML 2018 • He Zhao, Lan Du, Wray Buntine, Mingyuan Zhou
One important task of topic modeling for text analysis is interpretability.
no code implementations • 12 Feb 2018 • Yuan Jin, Mark Carman, Ye Zhu, Wray Buntine
Experiments show that our model(1) improves the performance of both quality control for crowd-sourced answers and next answer prediction for crowd-workers, and (2) can potentially provide coherent rankings of questions in terms of their difficulty and subjectivity, so that task providers can refine their designs of the crowdsourcing tasks, e. g. by removing highly subjective questions or inappropriately difficult questions.
1 code implementation • 19 Sep 2017 • He Zhao, Lan Du, Wray Buntine, Gang Liu
Besides the text content, documents and their associated words usually come with rich sets of meta informa- tion, such as categories of documents and semantic/syntactic features of words, like those encoded in word embeddings.
4 code implementations • 25 Aug 2017 • Francois Petitjean, Wray Buntine, Geoffrey I. Webb, Nayyar Zaidi
The main result of this paper is to show that improved parameter estimation allows BNCs to outperform leading learning methods such as Random Forest for both 0-1 loss and RMSE, albeit just on categorical datasets.
1 code implementation • ICML 2017 • He Zhao, Lan Du, Wray Buntine
Relational data are usually highly incomplete in practice, which inspires us to leverage side information to improve the performance of community detection and link prediction.
no code implementations • 22 Sep 2016 • Kar Wai Lim, Wray Buntine, Changyou Chen, Lan Du
In this article, we present efficient methods for the use of these processes in this hierarchical context, and apply them to latent variable models for text analytics.
no code implementations • 22 Sep 2016 • Kar Wai Lim, Changyou Chen, Wray Buntine
Exploiting this additional information, we propose the Twitter-Network (TN) topic model to jointly model the text and the social network in a full Bayesian nonparametric way.
no code implementations • 22 Sep 2016 • Kar Wai Lim, Wray Buntine
Bibliographic analysis considers author's research areas, the citation network and paper content among other things.
no code implementations • 21 Sep 2016 • Kar Wai Lim, Wray Buntine
In this paper, we combine these three in a topic model that produces a bibliographic model of authors, topics and documents, using a nonparametric extension of a combination of the Poisson mixed-topic link model and the author-topic model.
no code implementations • 21 Sep 2016 • Kar Wai Lim, Wray Buntine
Although social media data like tweets are laden with opinions, their "dirty" nature (as natural language) has discouraged researchers from applying LDA-based opinion model for product review mining.
no code implementations • NeurIPS 2011 • David Newman, Edwin V. Bonilla, Wray Buntine
To overcome this, we propose two methods to regularize the learning of topic models.
no code implementations • NeurIPS 2010 • James Petterson, Wray Buntine, Shravan M. Narayanamurthy, Tibério S. Caetano, Alex J. Smola
We extend Latent Dirichlet Allocation (LDA) by explicitly allowing for the encoding of side information in the distribution over words.