Mingbo Ma


2020

pdf bib
Opportunistic Decoding with Timely Correction for Simultaneous Translation
Renjie Zheng | Mingbo Ma | Baigong Zheng | Kaibo Liu | Liang Huang
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

Simultaneous translation has many important application scenarios and attracts much attention from both academia and industry recently. Most existing frameworks, however, have difficulties in balancing between the translation quality and latency, i.e., the decoding policy is usually either too aggressive or too conservative. We propose an opportunistic decoding technique with timely correction ability, which always (over-)generates a certain mount of extra words at each step to keep the audience on track with the latest information. At the same time, it also corrects, in a timely fashion, the mistakes in the former overgenerated words when observing more source context to ensure high translation quality. Experiments show our technique achieves substantial reduction in latency and up to +3.1 increase in BLEU, with revision rate under 8% in Chinese-to-English and English-to-Chinese translation.

pdf bib
Simultaneous Translation Policies: From Fixed to Adaptive
Baigong Zheng | Kaibo Liu | Renjie Zheng | Mingbo Ma | Hairong Liu | Liang Huang
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

Adaptive policies are better than fixed policies for simultaneous translation, since they can flexibly balance the tradeoff between translation quality and latency based on the current context information. But previous methods on obtaining adaptive policies either rely on complicated training process, or underperform simple fixed policies. We design an algorithm to achieve adaptive policies via a simple heuristic composition of a set of fixed policies. Experiments on Chinese -> English and German -> English show that our adaptive policies can outperform fixed ones by up to 4 BLEU points for the same latency, and more surprisingly, it even surpasses the BLEU score of full-sentence translation in the greedy mode (and very close to beam mode), but with much lower latency.

pdf bib
Incremental Text-to-Speech Synthesis with Prefix-to-Prefix Framework
Mingbo Ma | Baigong Zheng | Kaibo Liu | Renjie Zheng | Hairong Liu | Kainan Peng | Kenneth Church | Liang Huang
Findings of the Association for Computational Linguistics: EMNLP 2020

Text-to-speech synthesis (TTS) has witnessed rapid progress in recent years, where neural methods became capable of producing audios with high naturalness. However, these efforts still suffer from two types of latencies: (a) the computational latency (synthesizing time), which grows linearly with the sentence length, and (b) the input latency in scenarios where the input text is incrementally available (such as in simultaneous translation, dialog generation, and assistive technologies). To reduce these latencies, we propose a neural incremental TTS approach using the prefix-to-prefix framework from simultaneous translation. We synthesize speech in an online fashion, playing a segment of audio while generating the next, resulting in an O(1) rather than O(n) latency. Experiments on English and Chinese TTS show that our approach achieves similar speech naturalness compared to full sentence TTS, but only with a constant (1-2 words) latency.

pdf bib
Fluent and Low-latency Simultaneous Speech-to-Speech Translation with Self-adaptive Training
Renjie Zheng | Mingbo Ma | Baigong Zheng | Kaibo Liu | Jiahong Yuan | Kenneth Church | Liang Huang
Findings of the Association for Computational Linguistics: EMNLP 2020

Simultaneous speech-to-speech translation is an extremely challenging but widely useful scenario that aims to generate target-language speech only a few seconds behind the source-language speech. In addition, we have to continuously translate a speech of multiple sentences, but all recent solutions merely focus on the single-sentence scenario. As a result, current approaches will accumulate more and more latencies in later sentences when the speaker talks faster and introduce unnatural pauses into translated speech when the speaker talks slower. To overcome these issues, we propose Self-Adaptive Translation which flexibly adjusts the length of translations to accommodate different source speech rates. At similar levels of translation quality (as measured by BLEU), our method generates more fluent target speech latency than the baseline, in both Zh<->En directions.

pdf bib
Simultaneous Translation
Liang Huang | Colin Cherry | Mingbo Ma | Naveen Arivazhagan | Zhongjun He
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: Tutorial Abstracts

Simultaneous translation, which performs translation concurrently with the source speech, is widely useful in many scenarios such as international conferences, negotiations, press releases, legal proceedings, and medicine. This problem has long been considered one of the hardest problems in AI and one of its holy grails. Recently, with rapid improvements in machine translation, speech recognition, and speech synthesis, there has been exciting progress towards simultaneous translation. This tutorial will focus on the design and evaluation of policies for simultaneous translation, to leave attendees with a deep technical understanding of the history, the recent advances, and the remaining challenges in this field.

2019

pdf bib
Simpler and Faster Learning of Adaptive Policies for Simultaneous Translation
Baigong Zheng | Renjie Zheng | Mingbo Ma | Liang Huang
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)

Simultaneous translation is widely useful but remains challenging. Previous work falls into two main categories: (a) fixed-latency policies such as Ma et al. (2019) and (b) adaptive policies such as Gu et al. (2017). The former are simple and effective, but have to aggressively predict future content due to diverging source-target word order; the latter do not anticipate, but suffer from unstable and inefficient training. To combine the merits of both approaches, we propose a simple supervised-learning framework to learn an adaptive policy from oracle READ/WRITE sequences generated from parallel text. At each step, such an oracle sequence chooses to WRITE the next target word if the available source sentence context provides enough information to do so, otherwise READ the next source word. Experiments on German<=>English show that our method, without retraining the underlying NMT model, can learn flexible policies with better BLEU scores and similar latencies compared to previous work.

pdf bib
Speculative Beam Search for Simultaneous Translation
Renjie Zheng | Mingbo Ma | Baigong Zheng | Liang Huang
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)

Beam search is universally used in (full-sentence) machine translation but its application to simultaneous translation remains highly non-trivial, where output words are committed on the fly. In particular, the recently proposed wait-k policy (Ma et al., 2018) is a simple and effective method that (after an initial wait) commits one output word on receiving each input word, making beam search seemingly inapplicable. To address this challenge, we propose a new speculative beam search algorithm that hallucinates several steps into the future in order to reach a more accurate decision by implicitly benefiting from a target language model. This idea makes beam search applicable for the first time to the generation of a single word in each step. Experiments over diverse language pairs show large improvement compared to previous work.

pdf bib
STACL: Simultaneous Translation with Implicit Anticipation and Controllable Latency using Prefix-to-Prefix Framework
Mingbo Ma | Liang Huang | Hao Xiong | Renjie Zheng | Kaibo Liu | Baigong Zheng | Chuanqiang Zhang | Zhongjun He | Hairong Liu | Xing Li | Hua Wu | Haifeng Wang
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

Simultaneous translation, which translates sentences before they are finished, is use- ful in many scenarios but is notoriously dif- ficult due to word-order differences. While the conventional seq-to-seq framework is only suitable for full-sentence translation, we pro- pose a novel prefix-to-prefix framework for si- multaneous translation that implicitly learns to anticipate in a single translation model. Within this framework, we present a very sim- ple yet surprisingly effective “wait-k” policy trained to generate the target sentence concur- rently with the source sentence, but always k words behind. Experiments show our strat- egy achieves low latency and reasonable qual- ity (compared to full-sentence translation) on 4 directions: zh↔en and de↔en.

pdf bib
Robust Neural Machine Translation with Joint Textual and Phonetic Embedding
Hairong Liu | Mingbo Ma | Liang Huang | Hao Xiong | Zhongjun He
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

Neural machine translation (NMT) is notoriously sensitive to noises, but noises are almost inevitable in practice. One special kind of noise is the homophone noise, where words are replaced by other words with similar pronunciations. We propose to improve the robustness of NMT to homophone noises by 1) jointly embedding both textual and phonetic information of source sentences, and 2) augmenting the training dataset with homophone noises. Interestingly, to achieve better translation quality and more robustness, we found that most (though not all) weights should be put on the phonetic rather than textual information. Experiments show that our method not only significantly improves the robustness of NMT to homophone noises, but also surprisingly improves the translation quality on some clean test sets.

pdf bib
Simultaneous Translation with Flexible Policy via Restricted Imitation Learning
Baigong Zheng | Renjie Zheng | Mingbo Ma | Liang Huang
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

Simultaneous translation is widely useful but remains one of the most difficult tasks in NLP. Previous work either uses fixed-latency policies, or train a complicated two-staged model using reinforcement learning. We propose a much simpler single model that adds a “delay” token to the target vocabulary, and design a restricted dynamic oracle to greatly simplify training. Experiments on Chinese <-> English simultaneous translation show that our work leads to flexible policies that achieve better BLEU scores and lower latencies compared to both fixed and RL-learned policies.

pdf bib
Robust Machine Translation with Domain Sensitive Pseudo-Sources: Baidu-OSU WMT19 MT Robustness Shared Task System Report
Renjie Zheng | Hairong Liu | Mingbo Ma | Baigong Zheng | Liang Huang
Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1)

This paper describes the machine translation system developed jointly by Baidu Research and Oregon State University for WMT 2019 Machine Translation Robustness Shared Task. Translation of social media is a very challenging problem, since its style is very different from normal parallel corpora (e.g. News) and also include various types of noises. To make it worse, the amount of social media parallel corpora is extremely limited. In this paper, we use a domain sensitive training method which leverages a large amount of parallel data from popular domains together with a little amount of parallel data from social media. Furthermore, we generate a parallel dataset with pseudo noisy source sentences which are back-translated from monolingual data using a model trained by a similar domain sensitive way. In this way, we achieve more than 10 BLEU improvement in both En-Fr and Fr-En translation compared with the baseline methods.

pdf bib
Learning to Stop in Structured Prediction for Neural Machine Translation
Mingbo Ma | Renjie Zheng | Liang Huang
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)

Beam search optimization (Wiseman and Rush, 2016) resolves many issues in neural machine translation. However, this method lacks principled stopping criteria and does not learn how to stop during training, and the model naturally prefers longer hypotheses during the testing time in practice since they use the raw score instead of the probability-based score. We propose a novel ranking method which enables an optimal beam search stop- ping criteria. We further introduce a structured prediction loss function which penalizes suboptimal finished candidates produced by beam search during training. Experiments of neural machine translation on both synthetic data and real languages (German→English and Chinese→English) demonstrate our pro- posed methods lead to better length and BLEU score.

2018

pdf bib
Breaking the Beam Search Curse: A Study of (Re-)Scoring Methods and Stopping Criteria for Neural Machine Translation
Yilin Yang | Liang Huang | Mingbo Ma
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

Beam search is widely used in neural machine translation, and usually improves translation quality compared to greedy search. It has been widely observed that, however, beam sizes larger than 5 hurt translation quality. We explain why this happens, and propose several methods to address this problem. Furthermore, we discuss the optimal stopping criteria for these methods. Results show that our hyperparameter-free methods outperform the widely-used hyperparameter-free heuristic of length normalization by +2.0 BLEU, and achieve the best results among all methods on Chinese-to-English translation.

pdf bib
Multi-Reference Training with Pseudo-References for Neural Translation and Text Generation
Renjie Zheng | Mingbo Ma | Liang Huang
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

Neural text generation, including neural machine translation, image captioning, and summarization, has been quite successful recently. However, during training time, typically only one reference is considered for each example, even though there are often multiple references available, e.g., 4 references in NIST MT evaluations, and 5 references in image captioning data. We first investigate several different ways of utilizing multiple human references during training. But more importantly, we then propose an algorithm to generate exponentially many pseudo-references by first compressing existing human references into lattices and then traversing them to generate new pseudo-references. These approaches lead to substantial improvements over strong baselines in both machine translation (+1.5 BLEU) and image captioning (+3.1 BLEU / +11.7 CIDEr).

pdf bib
Ensemble Sequence Level Training for Multimodal MT: OSU-Baidu WMT18 Multimodal Machine Translation System Report
Renjie Zheng | Yilin Yang | Mingbo Ma | Liang Huang
Proceedings of the Third Conference on Machine Translation: Shared Task Papers

This paper describes multimodal machine translation systems developed jointly by Oregon State University and Baidu Research for WMT 2018 Shared Task on multimodal translation. In this paper, we introduce a simple approach to incorporate image information by feeding image features to the decoder side. We also explore different sequence level training methods including scheduled sampling and reinforcement learning which lead to substantial improvements. Our systems ensemble several models using different architectures and training methods and achieve the best performance for three subtasks: En-De and En-Cs in task 1 and (En+De+Fr)-Cs task 1B.

2017

pdf bib
Group Sparse CNNs for Question Classification with Answer Sets
Mingbo Ma | Liang Huang | Bing Xiang | Bowen Zhou
Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

Question classification is an important task with wide applications. However, traditional techniques treat questions as general sentences, ignoring the corresponding answer data. In order to consider answer information into question modeling, we first introduce novel group sparse autoencoders which refine question representation by utilizing group information in the answer set. We then propose novel group sparse CNNs which naturally learn question representation with respect to their answers by implanting group sparse autoencoders into traditional CNNs. The proposed model significantly outperform strong baselines on four datasets.

pdf bib
OSU Multimodal Machine Translation System Report
Mingbo Ma | Dapeng Li | Kai Zhao | Liang Huang
Proceedings of the Second Conference on Machine Translation

pdf bib
When to Finish? Optimal Beam Search for Neural Text Generation (modulo beam size)
Liang Huang | Kai Zhao | Mingbo Ma
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

In neural text generation such as neural machine translation, summarization, and image captioning, beam search is widely used to improve the output text quality. However, in the neural generation setting, hypotheses can finish in different steps, which makes it difficult to decide when to end beam search to ensure optimality. We propose a provably optimal beam search algorithm that will always return the optimal-score complete hypothesis (modulo beam size), and finish as soon as the optimality is established. To counter neural generation’s tendency for shorter hypotheses, we also introduce a bounded length reward mechanism which allows a modified version of our beam search algorithm to remain optimal. Experiments on neural machine translation demonstrate that our principled beam search algorithm leads to improvement in BLEU score over previously proposed alternatives.

2016

pdf bib
Textual Entailment with Structured Attentions and Composition
Kai Zhao | Liang Huang | Mingbo Ma
Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers

Deep learning techniques are increasingly popular in the textual entailment task, overcoming the fragility of traditional discrete models with hard alignments and logics. In particular, the recently proposed attention models (Rocktäschel et al., 2015; Wang and Jiang, 2015) achieves state-of-the-art accuracy by computing soft word alignments between the premise and hypothesis sentences. However, there remains a major limitation: this line of work completely ignores syntax and recursion, which is helpful in many traditional efforts. We show that it is beneficial to extend the attention model to tree nodes between premise and hypothesis. More importantly, this subtree-level attention reveals information about entailment relation. We study the recursive composition of this subtree-level entailment relation, which can be viewed as a soft version of the Natural Logic framework (MacCartney and Manning, 2009). Experiments show that our structured attention and entailment composition model can correctly identify and infer entailment relations from the bottom up, and bring significant improvements in accuracy.

2015

pdf bib
Dependency-based Convolutional Neural Networks for Sentence Embedding
Mingbo Ma | Liang Huang | Bowen Zhou | Bing Xiang
Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)