Search Results for author:
Found 59 papers, 20 papers with code
Hands-on Bayesian Neural Networks -- a Tutorial for Deep Learning Users
Modern deep learning methods constitute incredibly powerful tools to tackle a myriad of challenging problems.
All Labels Are Not Created Equal: Enhancing Semi-supervision via Label Grouping and Co-training
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.
Cross-Domain Graph Anomaly Detection via Anomaly-aware Contrastive Alignment
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.
PiVe: Prompting with Iterative Verification Improving Graph-based Generative Capability of LLMs
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.
$\mathtt{MedGraph:}$ Structural and Temporal Representation Learning of Electronic Medical Records
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.
Variational Autoencoders for Sparse and Overdispersed Discrete Data
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.
Neural Topic Model via Optimal Transport
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
Learning How to Actively Learn: A Deep Imitation Learning Approach
Heuristic-based active learning (AL) methods are limited when the data distribution of the underlying learning problems vary.
Gaussian Embedding of Large-scale Attributed Graphs
Graph embedding methods transform high-dimensional and complex graph contents into low-dimensional representations.
Ranked #1 on
Link Prediction
on Pubmed (nonstandard variant)
Accurate parameter estimation for Bayesian Network Classifiers using Hierarchical Dirichlet Processes
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.
Diversity Enhanced Active Learning with Strictly Proper Scoring Rules
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).
MetaLDA: a Topic Model that Efficiently Incorporates Meta information
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.
Dirichlet belief networks for topic structure learning
Recently, considerable research effort has been devoted to developing deep architectures for topic models to learn topic structures.
Inter and Intra Topic Structure Learning with Word Embeddings
One important task of topic modeling for text analysis is interpretability.
The Neglected Sibling: Isotropic Gaussian Posterior for VAE
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.
On the Effect of Isotropy on VAE Representations of Text
Injecting desired geometric properties into text representations has attracted a lot of attention.
Reward Engineering for Generating Semi-structured Explanation
Semi-structured explanation depicts the implicit process of a reasoner with an explicit representation.
Leveraging Node Attributes for Incomplete Relational Data
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.
Unsupervised Sentence Simplification via Dependency Parsing
Text simplification is the task of rewriting a text so that it is readable and easily understood.
SQAPlanner: Generating Data-Informed Software Quality Improvement Plans
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.
Distinguishing Question Subjectivity from Difficulty for Improved Crowdsourcing
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.
Bibliographic Analysis with the Citation Network Topic Model
Bibliographic analysis considers author's research areas, the citation network and paper content among other things.
Twitter-Network Topic Model: A Full Bayesian Treatment for Social Network and Text Modeling
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.
Nonparametric Bayesian Topic Modelling with the Hierarchical Pitman-Yor Processes
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.
Twitter Opinion Topic Model: Extracting Product Opinions from Tweets by Leveraging Hashtags and Sentiment Lexicon
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.
Bibliographic Analysis on Research Publications using Authors, Categorical Labels and the Citation Network
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.
Learning to Actively Learn Neural Machine Translation
Traditional active learning (AL) methods for machine translation (MT) rely on heuristics.
Adaptive Knowledge Sharing in Multi-Task Learning: Improving Low-Resource Neural Machine Translation
The routing network enables adaptive collaboration by dynamic sharing of blocks conditioned on the task at hand, input, and model state.
Improving Topic Coherence with Regularized Topic Models
To overcome this, we propose two methods to regularize the learning of topic models.
Word Features for Latent Dirichlet Allocation
We extend Latent Dirichlet Allocation (LDA) by explicitly allowing for the encoding of side information in the distribution over words.
Leveraging Meta Information in Short Text Aggregation
Short texts such as tweets often contain insufficient word co-occurrence information for training conventional topic models.
LoRMIkA: Local rule-based model interpretability with k-optimal associations
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.
Collective Wisdom: Improving Low-resource Neural Machine Translation using Adaptive Knowledge Distillation
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
Discriminative, Generative and Self-Supervised Approaches for Target-Agnostic Learning
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.
Temporal Cascade and Structural Modelling of EHRs for Granular Readmission Prediction
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.
Topic Modelling Meets Deep Neural Networks: A Survey
Topic modelling has been a successful technique for text analysis for almost twenty years.
Topic Model or Topic Twaddle? Re-evaluating Semantic Interpretability Measures
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.
Neural Attention-Aware Hierarchical Topic Model
Neural topic models (NTMs) apply deep neural networks to topic modelling.
Transformer over Pre-trained Transformer for Neural Text Segmentation with Enhanced Topic Coherence
This paper proposes a transformer over transformer framework, called Transformer$^2$, to perform neural text segmentation.
Multilingual Neural Machine Translation:Can Linguistic Hierarchies Help?
Multilingual Neural Machine Translation (MNMT) trains a single NMT model that supports translation between multiple languages, rather than training separate models for different languages.
Multilingual Neural Machine Translation: Can Linguistic Hierarchies Help?
Multilingual Neural Machine Translation (MNMT) trains a single NMT model that supports translation between multiple languages, rather than training separate models for different languages.
Curriculum Learning Effectively Improves Low Data VQA
In this paper, we propose curriculum-based learning (CL) regime to increase the accuracy of VQA models trained on small datasets.
Hardness-guided domain adaptation to recognise biomedical named entities under low-resource scenarios
Domain adaptation is an effective solution to data scarcity in low-resource scenarios.
AUC Maximization for Low-Resource Named Entity Recognition
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
Does Informativeness Matter? Active Learning for Educational Dialogue Act Classification
Then, the study investigates how the AL methods can select informative samples to support DA classifiers in the AL sampling process.
Robust Educational Dialogue Act Classifiers with Low-Resource and Imbalanced Datasets
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.
A Survey on Out-of-Distribution Evaluation of Neural NLP Models
Adversarial robustness, domain generalization and dataset biases are three active lines of research contributing to out-of-distribution (OOD) evaluation on neural NLP models.
Low-Resource Named Entity Recognition: Can One-vs-All AUC Maximization Help?
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.
HOMOE: A Memory-Based and Composition-Aware Framework for Zero-Shot Learning with Hopfield Network and Soft Mixture of Experts
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.
Bayesian Estimate of Mean Proper Scores for Diversity-Enhanced Active Learning
Expected Loss Reduction (ELR) focuses on a Bayesian estimate of the reduction in classification error, and more general costs fit in the same framework.
Harnessing the Power of Beta Scoring in Deep Active Learning for Multi-Label Text Classification
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.
Towards Uncertainty-Aware Language Agent
We present the Uncertainty-Aware Language Agent (UALA), a framework that orchestrates the interaction between the agent and the external world using uncertainty quantification.
OntoMedRec: Logically-Pretrained Model-Agnostic Ontology Encoders for Medication Recommendation
Most existing medication recommendation models learn representations for medical concepts based on electronic health records (EHRs) and make recommendations with learnt representations.
Improving Vietnamese-English Medical Machine Translation
Machine translation for Vietnamese-English in the medical domain is still an under-explored research area.
