31 citations · 69 across the 12 of their papers we have counts for
13 papers
Hierarchical Policy Optimization for Simultaneous Translation of Unbounded Speech
Siqi Ouyang, Shuoyang Ding, Oleksii Hrinchuk +4
Simultaneous speech translation (SST) generates translations while receiving partial speech input. Recent advances show that large language models (LLMs) can substantially improve…
Doubly-Trained Adversarial Data Augmentation for Neural Machine Translation
Weiting Tan, Shuoyang Ding, Huda Khayrallah +1
Neural Machine Translation (NMT) models are known to suffer from noisy inputs. To make models robust, we generate adversarial augmentation samples that attack the model and preserv…
The JHU-Microsoft Submission for WMT21 Quality Estimation Shared Task
Shuoyang Ding, Marcin Junczys-Dowmunt, Matt Post +2
This paper presents the JHU-Microsoft joint submission for WMT 2021 quality estimation shared task. We only participate in Task 2 (post-editing effort estimation) of the shared tas…
Levenshtein Training for Word-level Quality Estimation
Shuoyang Ding, Marcin Junczys-Dowmunt, Matt Post +1
We propose a novel scheme to use the Levenshtein Transformer to perform the task of word-level quality estimation. A Levenshtein Transformer is a natural fit for this task: trained…
Evaluating Saliency Methods for Neural Language Models
Shuoyang Ding, Philipp Koehn
Saliency methods are widely used to interpret neural network predictions, but different variants of saliency methods often disagree even on the interpretations of the same predicti…
Espresso: A Fast End-to-end Neural Speech Recognition Toolkit
Yiming Wang, Tongfei Chen, Hainan Xu +7
We present Espresso, an open-source, modular, extensible end-to-end neural automatic speech recognition (ASR) toolkit based on the deep learning library PyTorch and the popular neu…
Saliency-driven Word Alignment Interpretation for Neural Machine Translation
Shuoyang Ding, Hainan Xu, Philipp Koehn
Despite their original goal to jointly learn to align and translate, Neural Machine Translation (NMT) models, especially Transformer, are often perceived as not learning interpreta…
A Call for Prudent Choice of Subword Merge Operations in Neural Machine Translation
Shuoyang Ding, Adithya Renduchintala, Kevin Duh
Most neural machine translation systems are built upon subword units extracted by methods such as Byte-Pair Encoding (BPE) or wordpiece. However, the choice of number of merge oper…
Parallelizable Stack Long Short-Term Memory
Shuoyang Ding, Philipp Koehn
Stack Long Short-Term Memory (StackLSTM) is useful for various applications such as parsing and string-to-tree neural machine translation, but it is also known to be notoriously di…
Pretraining by Backtranslation for End-to-end ASR in Low-Resource Settings
Matthew Wiesner, Adithya Renduchintala, Shinji Watanabe +3
We explore training attention-based encoder-decoder ASR in low-resource settings. These models perform poorly when trained on small amounts of transcribed speech, in part because t…
Improving End-to-end Speech Recognition with Pronunciation-assisted Sub-word Modeling
Hainan Xu, Shuoyang Ding, Shinji Watanabe
Most end-to-end speech recognition systems model text directly as a sequence of characters or sub-words. Current approaches to sub-word extraction only consider character sequence…
How Do Source-side Monolingual Word Embeddings Impact Neural Machine Translation?
Shuoyang Ding, Kevin Duh
Using pre-trained word embeddings as input layer is a common practice in many natural language processing (NLP) tasks, but it is largely neglected for neural machine translation (N…
Multi-Modal Data Augmentation for End-to-End ASR
Adithya Renduchintala, Shuoyang Ding, Matthew Wiesner +1
We present a new end-to-end architecture for automatic speech recognition (ASR) that can be trained using \emph{symbolic} input in addition to the traditional acoustic input. This…