Search Results for author: Lan Du

Found 39 papers, 11 papers with code

Multilingual Neural Machine Translation: Can Linguistic Hierarchies Help?

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.

Knowledge Distillation Machine Translation +2

Towards Generalising Neural Topical Representations

no code implementations24 Jul 2023 Xiaohao Yang, He Zhao, Dinh Phung, Lan Du

Although NTMs have achieved promising performance when trained and tested on a specific corpus, their generalisation ability across corpora is rarely studied.

Data Augmentation Topic Models

Robust Educational Dialogue Act Classifiers with Low-Resource and Imbalanced Datasets

no code implementations15 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.

Multimodal Neural Processes for Uncertainty Estimation

no code implementations4 Apr 2023 Myong Chol Jung, He Zhao, Joanna Dipnall, Belinda Gabbe, Lan Du

For the first time, we propose a new model of NP family for multimodal uncertainty estimation, namely Multimodal Neural Processes.

Gaussian Processes

HiTSKT: A Hierarchical Transformer Model for Session-Aware Knowledge Tracing

no code implementations23 Dec 2022 Fucai Ke, Weiqing Wang, Weicong Tan, Lan Du, Yuan Jin, Yujin Huang, Hongzhi Yin

Knowledge tracing (KT) aims to leverage students' learning histories to estimate their mastery levels on a set of pre-defined skills, based on which the corresponding future performance can be accurately predicted.

Knowledge Tracing

Learning Semantic Textual Similarity via Topic-informed Discrete Latent Variables

1 code implementation7 Nov 2022 Erxin Yu, Lan Du, Yuan Jin, Zhepei Wei, Yi Chang

Recently, discrete latent variable models have received a surge of interest in both Natural Language Processing (NLP) and Computer Vision (CV), attributed to their comparable performance to the continuous counterparts in representation learning, while being more interpretable in their predictions.

Language Modelling Quantization +3

Uncertainty Estimation for Multi-view Data: The Power of Seeing the Whole Picture

no code implementations6 Oct 2022 Myong Chol Jung, He Zhao, Joanna Dipnall, Belinda Gabbe, Lan Du

Uncertainty estimation is essential to make neural networks trustworthy in real-world applications.

Diversity Enhanced Active Learning with Strictly Proper Scoring Rules

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).

Active Learning text-classification +1

Multilingual Neural Machine Translation:Can Linguistic Hierarchies Help?

no code implementations15 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.

Knowledge Distillation Machine Translation +2

Leveraging Information Bottleneck for Scientific Document Summarization

no code implementations Findings (EMNLP) 2021 Jiaxin Ju, Ming Liu, Huan Yee Koh, Yuan Jin, Lan Du, Shirui Pan

This paper presents an unsupervised extractive approach to summarize scientific long documents based on the Information Bottleneck principle.

Document Summarization Language Modelling +2

Prototype-Guided Memory Replay for Continual Learning

no code implementations28 Aug 2021 Stella Ho, Ming Liu, Lan Du, Longxiang Gao, Yong Xiang

Continual learning (CL) refers to a machine learning paradigm that learns continuously without forgetting previously acquired knowledge.

Continual Learning Meta-Learning +3

Learning Graph Neural Networks with Positive and Unlabeled Nodes

no code implementations8 Mar 2021 Man Wu, Shirui Pan, Lan Du, Xingquan Zhu

By generating multiple graphs at different distance levels, based on the adjacency matrix, we develop a long-short distance attention model to model these graphs.

Node Classification Transductive Learning

Stratified Sampling for Extreme Multi-Label Data

1 code implementation5 Mar 2021 Maximillian Merrillees, Lan Du

Extreme multi-label classification (XML) is becoming increasingly relevant in the era of big data.

Extreme Multi-Label Classification

Topic Modelling Meets Deep Neural Networks: A Survey

no code implementations28 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.

Navigate Text Generation +1

Collaborative Teacher-Student Learning via Multiple Knowledge Transfer

no code implementations21 Jan 2021 Liyuan Sun, Jianping Gou, Baosheng Yu, Lan Du, DaCheng Tao

However, most of the existing knowledge distillation methods consider only one type of knowledge learned from either instance features or instance relations via a specific distillation strategy in teacher-student learning.

Knowledge Distillation Model Compression +2

Multi-label Few/Zero-shot Learning with Knowledge Aggregated from Multiple Label Graphs

1 code implementation EMNLP 2020 Jueqing Lu, Lan Du, Ming Liu, Joanna Dipnall

Few/Zero-shot learning is a big challenge of many classifications tasks, where a classifier is required to recognise instances of classes that have very few or even no training samples.

Document Classification General Classification +3

SummPip: Unsupervised Multi-Document Summarization with Sentence Graph Compression

1 code implementation17 Jul 2020 Jinming Zhao, Ming Liu, Longxiang Gao, Yuan Jin, Lan Du, He Zhao, He Zhang, Gholamreza Haffari

Obtaining training data for multi-document summarization (MDS) is time consuming and resource-intensive, so recent neural models can only be trained for limited domains.

Clustering Document Summarization +1

Variational Auto-encoder Based Bayesian Poisson Tensor Factorization for Sparse and Imbalanced Count Data

no code implementations12 Oct 2019 Yuan Jin, Ming Liu, Yunfeng Li, Ruohua Xu, Lan Du, Longxiang Gao, Yong Xiang

Under synthetic data evaluation, VAE-BPTF tended to recover the right number of latent factors and posterior parameter values.

Leveraging Meta Information in Short Text Aggregation

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.

Clustering Topic Models

Variational Autoencoders for Sparse and Overdispersed Discrete Data

1 code implementation2 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.

Collaborative Filtering Multi-Label Learning +1

Dirichlet belief networks for topic structure learning

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.

Topic Models

Improving Topic Models with Latent Feature Word Representations

no code implementations TACL 2015 Dat Quoc Nguyen, Richard Billingsley, Lan Du, Mark Johnson

Probabilistic topic models are widely used to discover latent topics in document collections, while latent feature vector representations of words have been used to obtain high performance in many NLP tasks.

Clustering Document Classification +2

MetaLDA: a Topic Model that Efficiently Incorporates Meta information

1 code implementation19 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.

Topic Models Word Embeddings

Unsupervised Text Segmentation Based on Native Language Characteristics

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.

Text Segmentation

Leveraging Node Attributes for Incomplete Relational Data

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.

Community Detection Link Prediction

Nonparametric Bayesian Topic Modelling with the Hierarchical Pitman-Yor Processes

no code implementations22 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.

Topic Models

A Bayesian Model for Simultaneous Image Clustering, Annotation and Object Segmentation

no code implementations NeurIPS 2009 Lan Du, Lu Ren, Lawrence Carin, David B. Dunson

The model clusters the images into classes, and each image is segmented into a set of objects, also allowing the opportunity to assign a word to each object (localized labeling).

Clustering Image Clustering +1

Cannot find the paper you are looking for? You can Submit a new open access paper.