Search Results for author:
Found 21 papers, 5 papers with code
Underspecification in Natural Language Understanding for Dialog Automation
With the increasing number of communication platforms that offer variety of ways of connecting two interlocutors, there is a resurgence of chat-based dialog systems.
Bootstrapping Multilingual Intent Models via Machine Translation for Dialog Automation
With the resurgence of chat-based dialog systems in consumer and enterprise applications, there has been much success in developing data-driven and rule-based natural language models to understand human intent.
A k-Nearest Neighbor Approach towards Multi-level Sequence Labeling
For the experiments we perform a comparison between using pseudo-data and real world data.
Revisiting Consistent Hashing with Bounded Loads
We show, both theoretically and empirically, that our proposed solution is significantly superior for load balancing and is optimal in many senses.
Data Structures and Algorithms
Decaying momentum helps neural network training
Momentum is a simple and popular technique in deep learning for gradient-based optimizers.
Demon: Improved Neural Network Training with Momentum Decay
Momentum is a widely used technique for gradient-based optimizers in deep learning.
Negative sampling in semi-supervised learning
We introduce Negative Sampling in Semi-Supervised Learning (NS3L), a simple, fast, easy to tune algorithm for semi-supervised learning (SSL).
STORM: Foundations of End-to-End Empirical Risk Minimization on the Edge
To this end, we propose STORM, an online sketch for empirical risk minimization.
Exploring Text Specific and Blackbox Fairness Algorithms in Multimodal Clinical NLP
Clinical machine learning is increasingly multimodal, collected in both structured tabular formats and unstructured forms such as freetext.
StackMix: A complementary Mix algorithm
On its own, improvements with StackMix hold across different number of labeled samples on CIFAR-100, maintaining approximately a 2\% gap in test accuracy -- down to using only 5\% of the whole dataset -- and is effective in the semi-supervised setting with a 2\% improvement with the standard benchmark $\Pi$-model.
Transformer-Based Models for Question Answering on COVID19
In response to the Kaggle's COVID-19 Open Research Dataset (CORD-19) challenge, we have proposed three transformer-based question-answering systems using BERT, ALBERT, and T5 models.
Mitigating deep double descent by concatenating inputs
In this work, we explore the connection between the double descent phenomena and the number of samples in the deep neural network setting.
REX: Revisiting Budgeted Training with an Improved Schedule
Deep learning practitioners often operate on a computational and monetary budget.
STORM: Sketch Toward Online Risk Minimization
To this end, we propose STORM, an online sketching-based method for empirical risk minimization.
ChatLogo: A Large Language Model-Driven Hybrid Natural-Programming Language Interface for Agent-based Modeling and Programming
Building on Papert (1980)'s idea of children talking to computers, we propose ChatLogo, a hybrid natural-programming language interface for agent-based modeling and programming.
Fast FixMatch: Faster Semi-Supervised Learning with Curriculum Batch Size
Advances in Semi-Supervised Learning (SSL) have almost entirely closed the gap between SSL and Supervised Learning at a fraction of the number of labels.
A Smart System to Generate and Validate Question Answer Pairs for COVID-19 Literature
Automatically generating question answer (QA) pairs from the rapidly growing coronavirus-related literature is of great value to the medical community.
