b'David Chiang'

research

∙ 08/07/2023

Universal Automatic Phonetic Transcription into the International Phonetic Alphabet

This paper presents a state-of-the-art model for transcribing speech in ...

0 Chihiro Taguchi, et al. ∙

research

∙ 06/06/2023

Convergence and Diversity in the Control Hierarchy

Weir has defined a hierarchy of language classes whose second member (ℒ_...

0 Alexandra Butoi, et al. ∙

research

∙ 03/30/2023

Fine-Tuning BERT with Character-Level Noise for Zero-Shot Transfer to Dialects and Closely-Related Languages

In this work, we induce character-level noise in various forms when fine...

0 Aarohi Srivastava, et al. ∙

research

∙ 01/25/2023

Tighter Bounds on the Expressivity of Transformer Encoders

Characterizing neural networks in terms of better-understood formal syst...

0 David Chiang, et al. ∙

research

∙ 12/13/2022

Bridging Graph Position Encodings for Transformers with Weighted Graph-Walking Automata

A current goal in the graph neural network literature is to enable trans...

0 Patrick Soga, et al. ∙

research

∙ 10/19/2022

A Continuum of Generation Tasks for Investigating Length Bias and Degenerate Repetition

Language models suffer from various degenerate behaviors. These differ b...

0 Darcey Riley, et al. ∙

research

∙ 10/13/2022

Algorithms for Weighted Pushdown Automata

Weighted pushdown automata (WPDAs) are at the core of many natural langu...

0 Alexandra Butoi, et al. ∙

research

∙ 10/04/2022

The Surprising Computational Power of Nondeterministic Stack RNNs

Traditional recurrent neural networks (RNNs) have a fixed, finite number...

0 Brian DuSell, et al. ∙

research

∙ 10/03/2022

Exact Recursive Probabilistic Programming

Recursive calls over recursive data are widely useful for generating pro...

0 David Chiang, et al. ∙

research

∙ 02/24/2022

Overcoming a Theoretical Limitation of Self-Attention

Although transformers are remarkably effective for many tasks, there are...

0 David Chiang, et al. ∙

research

∙ 09/05/2021

Learning Hierarchical Structures with Differentiable Nondeterministic Stacks

Learning hierarchical structures in sequential data – from simple algori...

0 Brian DuSell, et al. ∙

research

∙ 05/04/2021

Data Augmentation by Concatenation for Low-Resource Translation: A Mystery and a Solution

In this paper, we investigate the driving factors behind concatenation, ...

0 Toan Q. Nguyen, et al. ∙

research

∙ 02/25/2021

Named Tensor Notation

We propose a notation for tensors with named axes, which relieves the au...

0 David Chiang, et al. ∙

research

∙ 10/22/2020

Translating Recursive Probabilistic Programs to Factor Graph Grammars

It is natural for probabilistic programs to use conditionals to express ...

0 David Chiang, et al. ∙

research

∙ 10/22/2020

Factor Graph Grammars

We propose the use of hyperedge replacement graph grammars for factor gr...

0 David Chiang, et al. ∙

research

∙ 10/12/2020

Look It Up: Bilingual and Monolingual Dictionaries Improve Neural Machine Translation

Despite advances in neural machine translation (NMT) quality, rare words...

0 Xing Jie Zhong, et al. ∙

research

∙ 10/09/2020

Learning Context-Free Languages with Nondeterministic Stack RNNs

We present a differentiable stack data structure that simultaneously and...

0 Brian DuSell, et al. ∙

research

∙ 01/02/2020

Representing Unordered Data Using Multiset Automata and Complex Numbers

Unordered, variable-sized inputs arise in many settings across multiple ...

0 Justin DeBenedetto, et al. ∙

research

∙ 10/16/2019

Efficiency through Auto-Sizing: Notre Dame NLP's Submission to the WNGT 2019 Efficiency Task

This paper describes the Notre Dame Natural Language Processing Group's ...

0 Kenton Murray, et al. ∙

research

∙ 10/01/2019

Auto-Sizing the Transformer Network: Improving Speed, Efficiency, and Performance for Low-Resource Machine Translation

Neural sequence-to-sequence models, particularly the Transformer, are th...

0 Kenton Murray, et al. ∙

research

∙ 08/29/2018

Correcting Length Bias in Neural Machine Translation

We study two problems in neural machine translation (NMT). First, in bea...

0 Kenton Murray, et al. ∙

research

∙ 08/19/2018

Neural Machine Translation of Text from Non-Native Speakers

Neural Machine Translation (NMT) systems are known to degrade when confr...

0 Alison Lui, et al. ∙

research

∙ 06/11/2018

Growing Better Graphs With Latent-Variable Probabilistic Graph Grammars

Recent work in graph models has found that probabilistic hyperedge repla...

0 Xinyi Wang, et al. ∙

research

∙ 06/11/2018

Part-of-Speech Tagging on an Endangered Language: a Parallel Griko-Italian Resource

Most work on part-of-speech (POS) tagging is focused on high resource la...

0 Antonis Anastasopoulos, et al. ∙

research

∙ 05/16/2018

Composing Finite State Transducers on GPUs

Weighted finite-state transducers (FSTs) are frequently used in language...

0 Arturo Argueta, et al. ∙

research

∙ 03/23/2018

Leveraging translations for speech transcription in low-resource settings

Recently proposed data collection frameworks for endangered language doc...

0 Antonis Anastasopoulos, et al. ∙

research

∙ 02/19/2018

Tied Multitask Learning for Neural Speech Translation

We explore multitask models for neural translation of speech, augmenting...

0 Antonios Anastasopoulos, et al. ∙

research

∙ 10/03/2017

Improving Lexical Choice in Neural Machine Translation

We explore two solutions to the problem of mistranslating rare words in ...

0 Toan Q. Nguyen, et al. ∙

research

∙ 08/31/2017

Transfer Learning across Low-Resource, Related Languages for Neural Machine Translation

We present a simple method to improve neural translation of a low-resour...

0 Toan Q. Nguyen, et al. ∙

research

∙ 07/18/2017

Top-Rank Enhanced Listwise Optimization for Statistical Machine Translation

Pairwise ranking methods are the basis of many widely used discriminativ...

0 Huadong Chen, et al. ∙

research

∙ 07/18/2017

Improved Neural Machine Translation with a Syntax-Aware Encoder and Decoder

Most neural machine translation (NMT) models are based on the sequential...

0 Huadong Chen, et al. ∙

research

∙ 02/14/2017

A case study on using speech-to-translation alignments for language documentation

For many low-resource or endangered languages, spoken language resources...

0 Antonios Anastasopoulos, et al. ∙

research

∙ 01/15/2017

DyNet: The Dynamic Neural Network Toolkit

We describe DyNet, a toolkit for implementing neural network models base...

0 Graham Neubig, et al. ∙

research

∙ 01/11/2017

Decoding with Finite-State Transducers on GPUs

Weighted finite automata and transducers (including hidden Markov models...

0 Arturo Argueta, et al. ∙

research

∙ 08/10/2016

Growing Graphs with Hyperedge Replacement Graph Grammars

Discovering the underlying structures present in large real world graphs...

0 Salvador Aguiñaga, et al. ∙

research

∙ 08/20/2015

Auto-Sizing Neural Networks: With Applications to n-gram Language Models

Neural networks have been shown to improve performance across a range of...

0 Kenton Murray, et al. ∙

David Chiang

Featured Co-authors