Search Results for author: Neil Mallinar

Found 8 papers, 1 papers with code

Unsupervised Adaptation of Question Answering Systems via Generative Self-training

no code implementations EMNLP 2020 Steven Rennie, Etienne Marcheret, Neil Mallinar, David Nahamoo, Vaibhava Goel

Nevertheless, additional pre-training closer to the end-task, such as training on synthetic QA pairs, has been shown to improve performance.

Question Answering

The Calibration Generalization Gap

no code implementations5 Oct 2022 A. Michael Carrell, Neil Mallinar, James Lucas, Preetum Nakkiran

We propose a systematic way to study the calibration error: by decomposing it into (1) calibration error on the train set, and (2) the calibration generalization gap.

Data Augmentation

Benign, Tempered, or Catastrophic: A Taxonomy of Overfitting

no code implementations14 Jul 2022 Neil Mallinar, James B. Simon, Amirhesam Abedsoltan, Parthe Pandit, Mikhail Belkin, Preetum Nakkiran

In this work we argue that while benign overfitting has been instructive and fruitful to study, many real interpolating methods like neural networks do not fit benignly: modest noise in the training set causes nonzero (but non-infinite) excess risk at test time, implying these models are neither benign nor catastrophic but rather fall in an intermediate regime.

Learning Theory

Iterative Data Programming for Expanding Text Classification Corpora

no code implementations4 Feb 2020 Neil Mallinar, Abhishek Shah, Tin Kam Ho, Rajendra Ugrani, Ayush Gupta

Real-world text classification tasks often require many labeled training examples that are expensive to obtain.

Denoising Ensemble Learning +4

Multi-Frame Cross-Entropy Training for Convolutional Neural Networks in Speech Recognition

no code implementations29 Jul 2019 Tom Sercu, Neil Mallinar

We introduce Multi-Frame Cross-Entropy training (MFCE) for convolutional neural network acoustic models.

speech-recognition Speech Recognition

Bootstrapping Conversational Agents With Weak Supervision

no code implementations14 Dec 2018 Neil Mallinar, Abhishek Shah, Rajendra Ugrani, Ayush Gupta, Manikandan Gurusankar, Tin Kam Ho, Q. Vera Liao, Yunfeng Zhang, Rachel K. E. Bellamy, Robert Yates, Chris Desmarais, Blake McGregor

We report on a user study that shows positive user feedback for this new approach to build conversational agents, and demonstrates the effectiveness of using data programming for auto-labeling.

Big-Little Net: An Efficient Multi-Scale Feature Representation for Visual and Speech Recognition

3 code implementations ICLR 2019 Chun-Fu Chen, Quanfu Fan, Neil Mallinar, Tom Sercu, Rogerio Feris

The proposed approach demonstrates improvement of model efficiency and performance on both object recognition and speech recognition tasks, using popular architectures including ResNet and ResNeXt.

Object Recognition speech-recognition +1

Deep Canonically Correlated LSTMs

no code implementations16 Jan 2018 Neil Mallinar, Corbin Rosset

We examine Deep Canonically Correlated LSTMs as a way to learn nonlinear transformations of variable length sequences and embed them into a correlated, fixed dimensional space.

Time Series Analysis

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