b'Kevin Duh'

research

∙ 06/20/2023

HK-LegiCoST: Leveraging Non-Verbatim Transcripts for Speech Translation

We introduce HK-LegiCoST, a new three-way parallel corpus of Cantonese-E...

0 Cihan Xiao, et al. ∙

research

∙ 06/12/2023

A Survey of Vision-Language Pre-training from the Lens of Multimodal Machine Translation

Large language models such as BERT and the GPT series started a paradigm...

0 Jeremy Gwinnup, et al. ∙

research

∙ 05/23/2023

Exploring Representational Disparities Between Multilingual and Bilingual Translation Models

Multilingual machine translation has proven immensely useful for low-res...

0 Neha Verma, et al. ∙

research

∙ 05/05/2023

In-context Learning as Maintaining Coherency: A Study of On-the-fly Machine Translation Using Large Language Models

The phenomena of in-context learning has typically been thought of as "l...

0 Suzanna Sia, et al. ∙

research

∙ 10/25/2022

Bilingual Lexicon Induction for Low-Resource Languages using Graph Matching via Optimal Transport

Bilingual lexicons form a critical component of various natural language...

0 Kelly Marchisio, et al. ∙

research

∙ 10/11/2022

IsoVec: Controlling the Relative Isomorphism of Word Embedding Spaces

The ability to extract high-quality translation dictionaries from monoli...

0 Kelly Marchisio, et al. ∙

research

∙ 01/20/2022

Transfer Learning Approaches for Building Cross-Language Dense Retrieval Models

The advent of transformer-based models such as BERT has led to the rise ...

12 Suraj Nair, et al. ∙

research

∙ 09/26/2021

An Analysis of Euclidean vs. Graph-Based Framing for Bilingual Lexicon Induction from Word Embedding Spaces

Much recent work in bilingual lexicon induction (BLI) views word embeddi...

0 Kelly Marchisio, et al. ∙

research

∙ 09/09/2021

Non-autoregressive End-to-end Speech Translation with Parallel Autoregressive Rescoring

This article describes an efficient end-to-end speech translation (E2E-S...

0 Hirofumi Inaguma, et al. ∙

research

∙ 07/01/2021

ESPnet-ST IWSLT 2021 Offline Speech Translation System

This paper describes the ESPnet-ST group's IWSLT 2021 submission in the ...

0 Hirofumi Inaguma, et al. ∙

research

∙ 05/10/2021

Self-Guided Curriculum Learning for Neural Machine Translation

In the field of machine learning, the well-trained model is assumed to b...

0 Lei Zhou, et al. ∙

research

∙ 01/26/2021

Leveraging End-to-End ASR for Endangered Language Documentation: An Empirical Study on Yoloxóchitl Mixtec

"Transcription bottlenecks", created by a shortage of effective human tr...

0 Jiatong Shi, et al. ∙

research

∙ 10/25/2020

Orthros: Non-autoregressive End-to-end Speech Translation with Dual-decoder

Fast inference speed is an important goal towards real-world deployment ...

0 Hirofumi Inaguma, et al. ∙

research

∙ 08/18/2020

Very Deep Transformers for Neural Machine Translation

We explore the application of very deep Transformer models for Neural Ma...

0 Xiaodong Liu, et al. ∙

research

∙ 05/08/2020

Modeling Document Interactions for Learning to Rank with Regularized Self-Attention

Learning to rank is an important task that has been successfully deploye...

0 Shuo Sun, et al. ∙

research

∙ 04/21/2020

ESPnet-ST: All-in-One Speech Translation Toolkit

We present ESPnet-ST, which is designed for the quick development of spe...

0 Hirofumi Inaguma, et al. ∙

research

∙ 04/12/2020

When Does Unsupervised Machine Translation Work?

Despite the reported success of unsupervised machine translation (MT), t...

0 Kelly Marchisio, et al. ∙

research

∙ 03/05/2020

Distill, Adapt, Distill: Training Small, In-Domain Models for Neural Machine Translation

We explore best practices for training small, memory efficient machine t...

0 Mitchell A. Gordon, et al. ∙

research

∙ 02/22/2020

Machine Translation System Selection from Bandit Feedback

Adapting machine translation systems in the real world is a difficult pr...

0 Jason Naradowsky, et al. ∙

research

∙ 02/19/2020

Compressing BERT: Studying the Effects of Weight Pruning on Transfer Learning

Universal feature extractors, such as BERT for natural language processi...

0 Mitchell A. Gordon, et al. ∙

research

∙ 12/06/2019

Explaining Sequence-Level Knowledge Distillation as Data-Augmentation for Neural Machine Translation

Sequence-level knowledge distillation (SLKD) is a model compression tech...

0 Mitchell A. Gordon, et al. ∙

research

∙ 10/01/2019

Multilingual End-to-End Speech Translation

In this paper, we propose a simple yet effective framework for multiling...

0 Hirofumi Inaguma, et al. ∙

research

∙ 09/05/2019

Broad-Coverage Semantic Parsing as Transduction

We unify different broad-coverage semantic parsing tasks under a transdu...

0 Sheng Zhang, et al. ∙

research

∙ 05/24/2019

A Call for Prudent Choice of Subword Merge Operations

Most neural machine translation systems are built upon subword units ext...

0 Shuoyang Ding, et al. ∙

research

∙ 05/21/2019

AMR Parsing as Sequence-to-Graph Transduction

We propose an attention-based model that treats AMR parsing as sequence-...

0 Sheng Zhang, et al. ∙

research

∙ 05/14/2019

Curriculum Learning for Domain Adaptation in Neural Machine Translation

We introduce a curriculum learning approach to adapt generic neural mach...

0 Xuan Zhang, et al. ∙

research

∙ 04/16/2019

Query Expansion for Cross-Language Question Re-Ranking

Community question-answering (CQA) platforms have become very popular fo...

0 Muhammad Mahbubur Rahman, et al. ∙

research

∙ 04/11/2019

Membership Inference Attacks on Sequence-to-Sequence Models

Data privacy is an important issue for "machine learning as a service" p...

0 Sorami Hisamoto, et al. ∙

research

∙ 11/02/2018

An Empirical Exploration of Curriculum Learning for Neural Machine Translation

Machine translation systems based on deep neural networks are expensive ...

0 Xuan Zhang, et al. ∙

research

∙ 10/30/2018

ReCoRD: Bridging the Gap between Human and Machine Commonsense Reading Comprehension

We present a large-scale dataset, ReCoRD, for machine reading comprehens...

0 Sheng Zhang, et al. ∙

research

∙ 09/24/2018

Stochastic Answer Networks for SQuAD 2.0

This paper presents an extension of the Stochastic Answer Network (SAN),...

0 Xiaodong Liu, et al. ∙

research

∙ 09/14/2018

Freezing Subnetworks to Analyze Domain Adaptation in Neural Machine Translation

To better understand the effectiveness of continued training, we analyze...

0 Brian Thompson, et al. ∙

research

∙ 09/06/2018

Character-Aware Decoder for Neural Machine Translation

Standard neural machine translation (NMT) systems operate primarily on w...

0 Adithya Renduchintala, et al. ∙

research

∙ 09/05/2018

BPE and CharCNNs for Translation of Morphology: A Cross-Lingual Comparison and Analysis

Neural Machine Translation (NMT) in low-resource settings and of morphol...

0 Pamela Shapiro, et al. ∙

research

∙ 06/05/2018

How Do Source-side Monolingual Word Embeddings Impact Neural Machine Translation?

Using pre-trained word embeddings as input layer is a common practice in...

0 Shuoyang Ding, et al. ∙

research

∙ 05/21/2018

Halo: Learning Semantics-Aware Representations for Cross-Lingual Information Extraction

Cross-lingual information extraction (CLIE) is an important and challeng...

0 Hongyuan Mei, et al. ∙

research

∙ 04/21/2018

Cross-lingual Semantic Parsing

We introduce the task of cross-lingual semantic parsing: mapping content...

0 Sheng Zhang, et al. ∙

research

∙ 04/21/2018

Fine-grained Entity Typing through Increased Discourse Context and Adaptive Classification Thresholds

Fine-grained entity typing is the task of assigning fine-grained semanti...

0 Sheng Zhang, et al. ∙

research

∙ 04/21/2018

Stochastic Answer Networks for Natural Language Inference

We propose a stochastic answer network (SAN) to explore multi-step infer...

0 Xiaodong Liu, et al. ∙

research

∙ 12/10/2017

Stochastic Answer Networks for Machine Reading Comprehension

We propose a simple yet robust stochastic answer network (SAN) that simu...

0 Xiaodong Liu, et al. ∙

research

∙ 11/09/2017

An Empirical Analysis of Multiple-Turn Reasoning Strategies in Reading Comprehension Tasks

Reading comprehension (RC) is a challenging task that requires synthesis...

0 Yelong Shen, et al. ∙

research

∙ 04/24/2017

Streaming Word Embeddings with the Space-Saving Algorithm

We develop a streaming (one-pass, bounded-memory) word embedding algorit...

0 Chandler May, 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

∙ 11/02/2016

Ordinal Common-sense Inference

Humans have the capacity to draw common-sense inferences from natural la...

0 Sheng Zhang, et al. ∙

research

∙ 08/07/2016

Robsut Wrod Reocginiton via semi-Character Recurrent Neural Network

Language processing mechanism by humans is generally more robust than co...

0 Keisuke Sakaguchi, et al. ∙

research

∙ 04/22/2016

Dependency Parsing with LSTMs: An Empirical Evaluation

We propose a transition-based dependency parser using Recurrent Neural N...

0 Adhiguna Kuncoro, et al. ∙

research

∙ 08/16/2015

Depth-Gated LSTM

In this short note, we present an extension of long short-term memory (L...

0 Kaisheng Yao, et al. ∙

research

∙ 12/18/2014

Incorporating Both Distributional and Relational Semantics in Word Representations

We investigate the hypothesis that word representations ought to incorpo...

0 Daniel Fried, et al. ∙

Kevin Duh

Featured Co-authors