Search Results for author: John Chen

Found 22 papers, 5 papers with code

A Smart System to Generate and Validate Question Answer Pairs for COVID-19 Literature

no code implementations EMNLP (sdp) 2020 Rohan Bhambhoria, Luna Feng, Dawn Sepehr, John Chen, Conner Cowling, Sedef Kocak, Elham Dolatabadi

Automatically generating question answer (QA) pairs from the rapidly growing coronavirus-related literature is of great value to the medical community.

Active Learning

A Network Simulation of OTC Markets with Multiple Agents

no code implementations3 May 2024 James T. Wilkinson, Jacob Kelter, John Chen, Uri Wilensky

We present a novel agent-based approach to simulating an over-the-counter (OTC) financial market in which trades are intermediated solely by market makers and agent visibility is constrained to a network topology.


Fast FixMatch: Faster Semi-Supervised Learning with Curriculum Batch Size

no code implementations7 Sep 2023 John Chen, Chen Dun, Anastasios Kyrillidis

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.

ChatLogo: A Large Language Model-Driven Hybrid Natural-Programming Language Interface for Agent-based Modeling and Programming

no code implementations16 Aug 2023 John Chen, Uri Wilensky

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.

Language Modelling Large Language Model

STORM: Sketch Toward Online Risk Minimization

no code implementations29 Sep 2021 Gaurav Gupta, Benjamin Coleman, John Chen, Anshumali Shrivastava

To this end, we propose STORM, an online sketching-based method for empirical risk minimization.

Classification regression

REX: Revisiting Budgeted Training with an Improved Schedule

1 code implementation9 Jul 2021 John Chen, Cameron Wolfe, Anastasios Kyrillidis

Deep learning practitioners often operate on a computational and monetary budget.

Mitigating deep double descent by concatenating inputs

no code implementations2 Jul 2021 John Chen, Qihan Wang, Anastasios Kyrillidis

In this work, we explore the connection between the double descent phenomena and the number of samples in the deep neural network setting.

Transformer-Based Models for Question Answering on COVID19

no code implementations16 Jan 2021 Hillary Ngai, Yoona Park, John Chen, Mahboobeh Parsapoor

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.

Question Answering

StackMix: A complementary Mix algorithm

no code implementations25 Nov 2020 John Chen, Samarth Sinha, Anastasios Kyrillidis

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.

Contrastive Learning Data Augmentation +1

Exploring Text Specific and Blackbox Fairness Algorithms in Multimodal Clinical NLP

1 code implementation EMNLP (ClinicalNLP) 2020 John Chen, Ian Berlot-Attwell, Safwan Hossain, Xindi Wang, Frank Rudzicz

Clinical machine learning is increasingly multimodal, collected in both structured tabular formats and unstructured forms such as freetext.

Fairness Word Embeddings

Negative sampling in semi-supervised learning

1 code implementation ICML 2020 John Chen, Vatsal Shah, Anastasios Kyrillidis

We introduce Negative Sampling in Semi-Supervised Learning (NS3L), a simple, fast, easy to tune algorithm for semi-supervised learning (SSL).

Demon: Improved Neural Network Training with Momentum Decay

2 code implementations11 Oct 2019 John Chen, Cameron Wolfe, Zhao Li, Anastasios Kyrillidis

Momentum is a widely used technique for gradient-based optimizers in deep learning.

Image Classification

Decaying momentum helps neural network training

no code implementations25 Sep 2019 John Chen, Anastasios Kyrillidis

Momentum is a simple and popular technique in deep learning for gradient-based optimizers.

Revisiting Consistent Hashing with Bounded Loads

1 code implementation23 Aug 2019 John Chen, Ben Coleman, Anshumali Shrivastava

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

Bootstrapping Multilingual Intent Models via Machine Translation for Dialog Automation

no code implementations11 May 2018 Nicholas Ruiz, Srinivas Bangalore, John Chen

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.

Machine Translation Translation

Underspecification in Natural Language Understanding for Dialog Automation

no code implementations RANLP 2017 John Chen, Srinivas Bangalore

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.

Natural Language Understanding Speech Recognition

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