Shuoyang Ding


2021

pdf bib
The JHU-Microsoft Submission for WMT21 Quality Estimation Shared Task
Shuoyang Ding | Marcin Junczys-Dowmunt | Matt Post | Christian Federmann | Philipp Koehn
Proceedings of the Sixth Conference on Machine Translation

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 task, focusing on the target-side word-level quality estimation. The techniques we experimented with include Levenshtein Transformer training and data augmentation with a combination of forward, backward, round-trip translation, and pseudo post-editing of the MT output. We demonstrate the competitiveness of our system compared to the widely adopted OpenKiwi-XLM baseline. Our system is also the top-ranking system on the MT MCC metric for the English-German language pair.

pdf bib
Levenshtein Training for Word-level Quality Estimation
Shuoyang Ding | Marcin Junczys-Dowmunt | Matt Post | Philipp Koehn
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

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 to perform decoding in an iterative manner, a Levenshtein Transformer can learn to post-edit without explicit supervision. To further minimize the mismatch between the translation task and the word-level QE task, we propose a two-stage transfer learning procedure on both augmented data and human post-editing data. We also propose heuristics to construct reference labels that are compatible with subword-level finetuning and inference. Results on WMT 2020 QE shared task dataset show that our proposed method has superior data efficiency under the data-constrained setting and competitive performance under the unconstrained setting.

pdf bib
Evaluating Saliency Methods for Neural Language Models
Shuoyang Ding | Philipp Koehn
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

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 prediction made by the same model. In these cases, how do we identify when are these interpretations trustworthy enough to be used in analyses? To address this question, we conduct a comprehensive and quantitative evaluation of saliency methods on a fundamental category of NLP models: neural language models. We evaluate the quality of prediction interpretations from two perspectives that each represents a desirable property of these interpretations: plausibility and faithfulness. Our evaluation is conducted on four different datasets constructed from the existing human annotation of syntactic and semantic agreements, on both sentence-level and document-level. Through our evaluation, we identified various ways saliency methods could yield interpretations of low quality. We recommend that future work deploying such methods to neural language models should carefully validate their interpretations before drawing insights.

2019

pdf bib
Parallelizable Stack Long Short-Term Memory
Shuoyang Ding | Philipp Koehn
Proceedings of the Third Workshop on Structured Prediction for NLP

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.

pdf bib
Saliency-driven Word Alignment Interpretation for Neural Machine Translation
Shuoyang Ding | Hainan Xu | Philipp Koehn
Proceedings of the Fourth Conference on Machine Translation (Volume 1: Research Papers)

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.

pdf bib
An Exploration of Placeholding in Neural Machine Translation
Matt Post | Shuoyang Ding | Marianna Martindale | Winston Wu
Proceedings of Machine Translation Summit XVII: Research Track

pdf bib
A Call for Prudent Choice of Subword Merge Operations in Neural Machine Translation
Shuoyang Ding | Adithya Renduchintala | Kevin Duh
Proceedings of Machine Translation Summit XVII: Research Track

2017

pdf bib
The JHU Machine Translation Systems for WMT 2017
Shuoyang Ding | Huda Khayrallah | Philipp Koehn | Matt Post | Gaurav Kumar | Kevin Duh
Proceedings of the Second Conference on Machine Translation

2016

pdf bib
The JHU Machine Translation Systems for WMT 2016
Shuoyang Ding | Kevin Duh | Huda Khayrallah | Philipp Koehn | Matt Post
Proceedings of the First Conference on Machine Translation: Volume 2, Shared Task Papers

2014

pdf bib
Grammatical Relations in Chinese: GB-Ground Extraction and Data-Driven Parsing
Weiwei Sun | Yantao Du | Xin Kou | Shuoyang Ding | Xiaojun Wan
Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)