Search Results for author:
Found 45 papers, 33 papers with code
An Interpretable Ensemble of Graph and Language Models for Improving Search Relevance in E-Commerce
This lack of interpretability hinders the development and adoption of new techniques in the field.
Discovery of Generalizable TBI Phenotypes Using Multivariate Time-Series Clustering
Importantly, while certain features varied by age, the core characteristics of TBI manifestations tied to each phenotype remain consistent across diverse populations.
ViSAGe: A Global-Scale Analysis of Visual Stereotypes in Text-to-Image Generation
First, we show that stereotypical attributes in ViSAGe are thrice as likely to be present in generated images of corresponding identities as compared to other attributes, and that the offensiveness of these depictions is especially higher for identities from Africa, South America, and South East Asia.
SNIP: Bridging Mathematical Symbolic and Numeric Realms with Unified Pre-training
To bridge the gap, we introduce SNIP, a Symbolic-Numeric Integrated Pre-training model, which employs contrastive learning between symbolic and numeric domains, enhancing their mutual similarities in the embeddings.
SeeGULL: A Stereotype Benchmark with Broad Geo-Cultural Coverage Leveraging Generative Models
Stereotype benchmark datasets are crucial to detect and mitigate social stereotypes about groups of people in NLP models.
Complex Logical Reasoning over Knowledge Graphs using Large Language Models
Reasoning over knowledge graphs (KGs) is a challenging task that requires a deep understanding of the complex relationships between entities and the underlying logic of their relations.
Identifying TBI Physiological States by Clustering Multivariate Clinical Time-Series Data
Determining clinically relevant physiological states from multivariate time series data with missing values is essential for providing appropriate treatment for acute conditions such as Traumatic Brain Injury (TBI), respiratory failure, and heart failure.
Transformer-based Planning for Symbolic Regression
Unlike conventional decoding strategies, TPSR enables the integration of non-differentiable feedback, such as fitting accuracy and complexity, as external sources of knowledge into the transformer-based equation generation process.
A Self-Supervised Learning-based Approach to Clustering Multivariate Time-Series Data with Missing Values (SLAC-Time): An Application to TBI Phenotyping
To address these challenges, we present a Self-supervised Learning-based Approach to Clustering multivariate Time-series data with missing values (SLAC-Time).
Transformer-based Models for Long-Form Document Matching: Challenges and Empirical Analysis
Firstly, the performance gain provided by transformer-based models comes at a steep cost - both in terms of the required training time and the resource (memory and energy) consumption.
Execution-based Code Generation using Deep Reinforcement Learning
It's important to note that PPOCoder is a task-agnostic and model-agnostic framework that can be used across different code generation tasks and PLs.
An Empirical Comparison of Explainable Artificial Intelligence Methods for Clinical Data: A Case Study on Traumatic Brain Injury
The implemented methods were compared to one another in terms of several XAI characteristics such as understandability, fidelity, and stability.
Explainable artificial intelligence
Explainable Artificial Intelligence (XAI)
+2
Text Enriched Sparse Hyperbolic Graph Convolutional Networks
In TESH-GCN, we extract semantic node information, which successively acts as a connection signal to extract relevant nodes' local neighborhood and graph-level metapath features from the sparse adjacency tensor in a reformulated hyperbolic graph convolution layer.
XLCoST: A Benchmark Dataset for Cross-lingual Code Intelligence
To the best of our knowledge, it is the largest parallel dataset for source code both in terms of size and the number of languages.
Shopping Queries Dataset: A Large-Scale ESCI Benchmark for Improving Product Search
This paper introduces the "Shopping Queries Dataset", a large dataset of difficult Amazon search queries and results, publicly released with the aim of fostering research in improving the quality of search results.
StructCoder: Structure-Aware Transformer for Code Generation
This paper addresses the problem of code generation, where the goal is to generate target code given source code in a different language or a natural language description.
A Unification Framework for Euclidean and Hyperbolic Graph Neural Networks
Such an approach enables us to propose a hyperbolic normalization layer and to further simplify the entire hyperbolic model to a Euclidean model cascaded with our hyperbolic normalization layer.
Towards Scalable Hyperbolic Neural Networks using Taylor Series Approximations
However, their adoption in practice remains restricted due to (i) non-scalability on accelerated deep learning hardware, (ii) vanishing gradients due to the closure of hyperbolic space, and (iii) information loss due to frequent mapping between local tangent space and fully hyperbolic space.
CodeAttack: Code-Based Adversarial Attacks for Pre-trained Programming Language Models
Pre-trained programming language (PL) models (such as CodeT5, CodeBERT, GraphCodeBERT, etc.,) have the potential to automate software engineering tasks involving code understanding and code generation.
Multi-Label Clinical Time-Series Generation via Conditional GAN
In this work, we propose a Multi-label Time-series GAN (MTGAN) to generate EHR and simultaneously improve the quality of uncommon disease generation.
Probabilistic Entity Representation Model for Reasoning over Knowledge Graphs
Current approaches employ spatial geometries such as boxes to learn query representations that encompass the answer entities and model the logical operations of projection and intersection.
Supervised Contrastive Learning for Interpretable Long-Form Document Matching
When handling such long documents, there are three primary challenges: (i) the presence of different contexts for the same word throughout the document, (ii) small sections of contextually similar text between two documents, but dissimilar text in the remaining parts (this defies the basic understanding of "similarity"), and (iii) the coarse nature of a single global similarity measure which fails to capture the heterogeneity of the document content.
Attention-based Aspect Reasoning for Knowledge Base Question Answering on Clinical Notes
On the other hand, the aspects, entity and context, limit the answers by node-specific information and lead to higher precision and lower recall.
Knowledge Base Question Answering
Machine Reading Comprehension
Fair Representation Learning using Interpolation Enabled Disentanglement
In this paper, we propose a novel method to address two key issues: (a) Can we simultaneously learn fair disentangled representations while ensuring the utility of the learned representation for downstream tasks, and (b)Can we provide theoretical insights into when the proposed approach will be both fair and accurate.
Self-Supervised Transformer for Sparse and Irregularly Sampled Multivariate Clinical Time-Series
In addition, to tackle the problem of limited availability of labeled data (which is typically observed in many healthcare applications), STraTS utilizes self-supervision by leveraging unlabeled data to learn better representations by using time-series forecasting as an auxiliary proxy task.
Self-Supervised Graph Learning with Hyperbolic Embedding for Temporal Health Event Prediction
Electronic Health Records (EHR) have been heavily used in modern healthcare systems for recording patients' admission information to hospitals.
Collaborative Graph Learning with Auxiliary Text for Temporal Event Prediction in Healthcare
Accurate and explainable health event predictions are becoming crucial for healthcare providers to develop care plans for patients.
Jekyll: Attacking Medical Image Diagnostics using Deep Generative Models
The potential for fraudulent claims based on such generated 'fake' medical images is significant, and we demonstrate successful attacks on both X-rays and retinal fundus image modalities.
T-Miner: A Generative Approach to Defend Against Trojan Attacks on DNN-based Text Classification
T-Miner employs a sequence-to-sequence (seq-2-seq) generative model that probes the suspicious classifier and learns to produce text sequences that are likely to contain the Trojan trigger.
Self-Supervised Hyperboloid Representations from Logical Queries over Knowledge Graphs
Promising approaches to tackle this problem include embedding the KG units (e. g., entities and relations) in a Euclidean space such that the query embedding contains the information relevant to its results.
Differentially Private Synthetic Medical Data Generation using Convolutional GANs
Deep learning models have demonstrated superior performance in several application problems, such as image classification and speech processing.
Question Answering with Long Multiple-Span Answers
To this end, we present MASH-QA, a Multiple Answer Spans Healthcare Question Answering dataset from the consumer health domain, where answers may need to be excerpted from multiple, non-consecutive parts of text spanned across a long document.
A Simple and Effective Self-Supervised Contrastive Learning Framework for Aspect Detection
However, recent deep learning-based topic models, specifically aspect-based autoencoder, suffer from several problems, such as extracting noisy aspects and poorly mapping aspects discovered by models to the aspects of interest.
An Interpretable and Uncertainty Aware Multi-Task Framework for Multi-Aspect Sentiment Analysis
In addition, we also propose an Attention-driven Keywords Ranking (AKR) method, which can automatically discover aspect keywords and aspect-level opinion keywords from the review corpus based on the attention weights.
Self-Supervised Learning of Contextual Embeddings for Link Prediction in Heterogeneous Networks
Representation learning methods for heterogeneous networks produce a low-dimensional vector embedding for each node that is typically fixed for all tasks involving the node.
Corpus-level and Concept-based Explanations for Interpretable Document Classification
In this paper, we propose a corpus-level explanation approach, which aims to capture causal relationships between keywords and model predictions via learning the importance of keywords for predicted labels across a training corpus based on attention weights.
Image Generation Via Minimizing Fréchet Distance in Discriminator Feature Space
We use the intuition that it is much better to train the GAN generator by minimizing the distributional distance between real and generated images in a small dimensional feature space representing such a manifold than on the original pixel-space.
Image Hashing by Minimizing Discrete Component-wise Wasserstein Distance
In this paper, we show that the high sample-complexity requirement often results in sub-optimal retrieval performance of the adversarial hashing methods.
LATTE: Latent Type Modeling for Biomedical Entity Linking
This is of significant importance in the biomedical domain, where it could be used to semantically annotate a large volume of clinical records and biomedical literature, to standardized concepts described in an ontology such as Unified Medical Language System (UMLS).
Text-to-SQL Generation for Question Answering on Electronic Medical Records
In this paper, we tackle these challenges by developing a deep learning based TRanslate-Edit Model for Question-to-SQL (TREQS) generation, which adapts the widely used sequence-to-sequence model to directly generate the SQL query for a given question, and further performs the required edits using an attentive-copying mechanism and task-specific look-up tables.
LeafNATS: An Open-Source Toolkit and Live Demo System for Neural Abstractive Text Summarization
Neural abstractive text summarization (NATS) has received a lot of attention in the past few years from both industry and academia.
Neural Abstractive Text Summarization with Sequence-to-Sequence Models
As part of this survey, we also develop an open source library, namely, Neural Abstractive Text Summarizer (NATS) toolkit, for the abstractive text summarization.
Deep Transfer Reinforcement Learning for Text Summarization
Deep neural networks are data hungry models and thus face difficulties when attempting to train on small text datasets.
Deep Reinforcement Learning For Sequence to Sequence Models
In this survey, we consider seq2seq problems from the RL point of view and provide a formulation combining the power of RL methods in decision-making with sequence-to-sequence models that enable remembering long-term memories.
Machine Learning for Survival Analysis: A Survey
We hope that this paper will provide a more thorough understanding of the recent advances in survival analysis and offer some guidelines on applying these approaches to solve new problems that arise in applications with censored data.
