Shuoyang Ding

Shuoyang Ding

Auto-generated profile, based on publicly available information

Shuoyang Ding

Center of Language and Speech Processing

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
14 June 2018 in arXiv
Verified
Preprint
Open access
PDF file
SDShuoyang Ding
Shuoyang Ding
KDKevin Duh
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 (NMT). In this paper, we conducted a systematic analysis on the effect of using pre-trained source-side monolingual word embedding in NMT. We compared several strategies, such as fixing or updating the embeddings during NMT training on varying amounts of data, and we also proposed a novel strategy called dual-embedding that blends the fixing and updating strategies. Our results suggest that pre-trained embeddings can be helpful if properly incorporated into NMT, especially when parallel data is limited or additional in-domain monolingual data is readily available.

18 June 2018 in arXiv
Verified
Preprint
Open access
PDF file
ARAdithya Renduchintala
Adithya Renduchintala
SDShuoyang Ding
Shuoyang Ding
MWMatthew Wiesner
Matthew Wiesner
SWShinji Watanabe
Shinji Watanabe
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 architecture utilizes two separate encoders: one for acoustic input and another for symbolic input, both sharing the attention and decoder parameters. We call this architecture a multi-modal data augmentation network (MMDA), as it can support multi-modal (acoustic and symbolic) input and enables seamless mixing of large text datasets with significantly smaller transcribed speech corpora during training. We study different ways of transforming large text corpora into a symbolic form suitable for training our MMDA network. Our best MMDA setup obtains small improvements on character error rate (CER), and as much as 7-10\% relative word error rate (WER) improvement over a baseline both with and without an external language model.

27 June 2019 in arXiv
Verified
Preprint
Open access
PDF file
SDShuoyang Ding
Shuoyang Ding
HXHainan Xu
Hainan Xu
PKPhilipp Koehn
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 interpretable word alignments. In this paper, we show that NMT models do learn interpretable word alignments, which could only be revealed with proper interpretation methods. We propose a series of such methods that are model-agnostic, are able to be applied either offline or online, and do not require parameter update or architectural change. We show that under the force decoding setup, the alignments induced by our interpretation method are of better quality than fast-align for some systems, and when performing free decoding, they agree well with the alignments induced by automatic alignment tools.

6 April 2019 in arXiv
Verified
Preprint
Open access
PDF file
SDShuoyang Ding
Shuoyang Ding
PKPhilipp Koehn
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 difficult to parallelize for GPU training due to the fact that the computations are dependent on discrete operations. In this paper, we tackle this problem by utilizing state access patterns of StackLSTM to homogenize computations with regard to different discrete operations. Our parsing experiments show that the method scales up almost linearly with increasing batch size, and our parallelized PyTorch implementation trains significantly faster compared to the Dynet C++ implementation.

24 June 2019 in arXiv
Verified
Preprint
Open access
PDF file
SDShuoyang Ding
Shuoyang Ding
ARAdithya Renduchintala
Adithya Renduchintala
KDKevin Duh
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 operations is generally made by following existing recipes. In this paper, we conduct a systematic exploration on different numbers of BPE merge operations to understand how it interacts with the model architecture, the strategy to build vocabularies and the language pair. Our exploration could provide guidance for selecting proper BPE configurations in the future. Most prominently: we show that for LSTM-based architectures, it is necessary to experiment with a wide range of different BPE operations as there is no typical optimal BPE configuration, whereas for Transformer architectures, smaller BPE size tends to be a typically optimal choice. We urge the community to make prudent choices with subword merge operations, as our experiments indicate that a sub-optimal BPE configuration alone could easily reduce the system performance by 3-4 BLEU points.

21 February 2019 in arXiv
Verified
Preprint
Open access
PDF file
HXHainan Xu
Hainan Xu
SDShuoyang Ding
Shuoyang Ding
SWShinji Watanabe
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 frequencies, which at times produce inferior sub-word segmentation that might lead to erroneous speech recognition output. We propose pronunciation-assisted sub-word modeling (PASM), a sub-word extraction method that leverages the pronunciation information of a word. Experiments show that the proposed method can greatly improve upon the character-based baseline, and also outperform commonly used byte-pair encoding methods.