Consistency regularization methods, such as R-Drop (Liang et al., 2021) and CrossConST (Gao et al., 2023), have achieved impressive supervised and zero-shot performance in the neural machine translation (NMT) field. Can we also boost end-to-end (E2E) speech-to-text translation (ST) by leveraging consistency regularization? In this paper, we conduct empirical studies on intra-modal and cross-modal consistency and propose two training strategies, SimRegCR and SimZeroCR, for E2E ST in regular and zero-shot scenarios. Experiments on the MuST-C benchmark show that our approaches achieve state-of-the-art (SOTA) performance in most translation directions. The analyses prove that regularization brought by the intra-modal consistency, instead of the modality gap, is crucial for the regular E2E ST, and the cross-modal consistency could close the modality gap and boost the zero-shot E2E ST performance.

The multilingual neural machine translation (NMT) model has a promising capability of zero-shot translation, where it could directly translate between language pairs unseen during training. For good transfer performance from supervised directions to zero-shot directions, the multilingual NMT model is expected to learn universal representations across different languages. This paper introduces a cross-lingual consistency regularization, CrossConST, to bridge the representation gap among different languages and boost zero-shot translation performance. The theoretical analysis shows that CrossConST implicitly maximizes the probability distribution for zero-shot translation, and the experimental results on both low-resource and high-resource benchmarks show that CrossConST consistently improves the translation performance. The experimental analysis also proves that CrossConST could close the sentence representation gap and better align the representation space. Given the universality and simplicity of CrossConST, we believe it can serve as a strong baseline for future multilingual NMT research.

Multilingual sentence representations are the foundation for similarity-based bitext mining, which is crucial for scaling multilingual neural machine translation (NMT) system to more languages. In this paper, we introduce MuSR: a one-for-all Multilingual Sentence Representation model that supports 223 languages. Leveraging billions of English-centric parallel corpora, we train a multilingual Transformer encoder, coupled with an auxiliary Transformer decoder, by adopting a multilingual NMT framework with CrossConST, a cross-lingual consistency regularization technique proposed in Gao et al. (2023). Experimental results on multilingual similarity search and bitext mining tasks show the effectiveness of our approach. Specifically, MuSR achieves superior performance over LASER3 (Heffernan et al., 2022) which consists of 148 independent multilingual sentence encoders.

We introduce Bi-SimCut: a simple but effective training strategy to boost neural machine translation (NMT) performance. It consists of two procedures: bidirectional pretraining and unidirectional finetuning. Both procedures utilize SimCut, a simple regularization method that forces the consistency between the output distributions of the original and the cutoff sentence pairs. Without leveraging extra dataset via back-translation or integrating large-scale pretrained model, Bi-SimCut achieves strong translation performance across five translation benchmarks (data sizes range from 160K to 20.2M): BLEU scores of 31.16 for en→de and 38.37 for de→en on the IWSLT14 dataset, 30.78 for en→de and 35.15 for de→en on the WMT14 dataset, and 27.17 for zh→en on the WMT17 dataset. SimCut is not a new method, but a version of Cutoff (Shen et al., 2020) simplified and adapted for NMT, and it could be considered as a perturbation-based method. Given the universality and simplicity of Bi-SimCut and SimCut, we believe they can serve as strong baselines for future NMT research.

Automatic Speech Recognition (ASR) is an efficient and widely used input method that transcribes speech signals into text. As the errors introduced by ASR systems will impair the performance of downstream tasks, we introduce a post-processing error correction method, PhVEC, to correct errors in text space. For the errors in ASR result, existing works mainly focus on fixed-length corrections, modifying each wrong token to a correct one (one-to-one correction), but rarely consider the variable-length correction (one-to-many or many-to-one correction). In this paper, we propose an efficient non-autoregressive (NAR) method for Chinese ASR error correction for both cases. Instead of conventionally predicting the sentence length in NAR methods, we propose a novel approach that uses phonological tokens to extend the source sentence for variable-length correction, enabling our model to generate phonetically similar corrections. Experimental results on datasets of different domains show that our method achieves significant improvement in word error rate reduction and speeds up the inference by 6.2 times compared with the autoregressive model.

This paper reports the results of the shared task we hosted on the Third Workshop of Automatic Simultaneous Translation (AutoSimTrans). The shared task aims to promote the development of text-to-text and speech-to-text simultaneous translation, and includes Chinese-English and English-Spanish tracks. The number of systems submitted this year has increased fourfold compared with last year. Additionally, the top 1 ranked system in the speech-to-text track is the first end-to-end submission we have received in the past three years, which has shown great potential. This paper reports the results and descriptions of the 14 participating teams, compares different evaluation metrics, and revisits the ranking method.

End-to-end simultaneous speech-to-text translation aims to directly perform translation from streaming source speech to target text with high translation quality and low latency. A typical simultaneous translation (ST) system consists of a speech translation model and a policy module, which determines when to wait and when to translate. Thus the policy is crucial to balance translation quality and latency. Conventional methods usually adopt fixed policies, e.g. segmenting the source speech with a fixed length and generating translation. However, this method ignores contextual information and suffers from low translation quality. This paper proposes an adaptive segmentation policy for end-to-end ST. Inspired by human interpreters, the policy learns to segment the source streaming speech into meaningful units by considering both acoustic features and translation history, maintaining consistency between the segmentation and translation. Experimental results on English-German and Chinese-English show that our method achieves a good accuracy-latency trade-off over recently proposed state-of-the-art methods.

This paper presents BSTC (Baidu Speech Translation Corpus), a large-scale Chinese-English speech translation dataset. This dataset is constructed based on a collection of licensed videos of talks or lectures, including about 68 hours of Mandarin data, their manual transcripts and translations into English, as well as automated transcripts by an automatic speech recognition (ASR) model. We have further asked three experienced interpreters to simultaneously interpret the testing talks in a mock conference setting. This corpus is expected to promote the research of automatic simultaneous translation as well as the development of practical systems. We have organized simultaneous translation tasks and used this corpus to evaluate automatic simultaneous translation systems.

This paper presents the results of the shared task of the 2nd Workshop on Automatic Simultaneous Translation (AutoSimTrans). The task includes two tracks, one for text-to-text translation and one for speech-to-text, requiring participants to build systems to translate from either the source text or speech into the target text. Different from traditional machine translation, the AutoSimTrans shared task evaluates not only translation quality but also latency. We propose a metric “Monotonic Optimal Sequence” (MOS) considering both quality and latency to rank the submissions. We also discuss some important open issues in simultaneous translation.

Diverse machine translation aims at generating various target language translations for a given source language sentence. To leverage the linear relationship in the sentence latent space introduced by the mixup training, we propose a novel method, MixDiversity, to generate different translations for the input sentence by linearly interpolating it with different sentence pairs sampled from the training corpus during decoding. To further improve the faithfulness and diversity of the translations, we propose two simple but effective approaches to select diverse sentence pairs in the training corpus and adjust the interpolation weight for each pair correspondingly. Moreover, by controlling the interpolation weight, our method can achieve the trade-off between faithfulness and diversity without any additional training, which is required in most of the previous methods. Experiments on WMT’16 en-ro, WMT’14 en-de, and WMT’17 zh-en are conducted to show that our method substantially outperforms all previous diverse machine translation methods.

Balancing accuracy and latency is a great challenge for simultaneous translation. To achieve high accuracy, the model usually needs to wait for more streaming text before translation, which results in increased latency. However, keeping low latency would probably hurt accuracy. Therefore, it is essential to segment the ASR output into appropriate units for translation. Inspired by human interpreters, we propose a novel adaptive segmentation policy for simultaneous translation. The policy learns to segment the source text by considering possible translations produced by the translation model, maintaining consistency between the segmentation and translation. Experimental results on Chinese-English and German-English translation show that our method achieves a better accuracy-latency trade-off over recently proposed state-of-the-art methods.

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.

In this paper we introduce the systems Baidu submitted for the WMT19 shared task on Chinese<->English news translation. Our systems are based on the Transformer architecture with some effective improvements. Data selection, back translation, data augmentation, knowledge distillation, domain adaptation, model ensemble and re-ranking are employed and proven effective in our experiments. Our Chinese->English system achieved the highest case-sensitive BLEU score among all constrained submissions, and our English->Chinese system ranked the second in all submissions.

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.

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.

Conventional Neural Machine Translation (NMT) models benefit from the training with an additional agent, e.g., dual learning, and bidirectional decoding with one agent decod- ing from left to right and the other decoding in the opposite direction. In this paper, we extend the training framework to the multi-agent sce- nario by introducing diverse agents in an in- teractive updating process. At training time, each agent learns advanced knowledge from others, and they work together to improve translation quality. Experimental results on NIST Chinese-English, IWSLT 2014 German- English, WMT 2014 English-German and large-scale Chinese-English translation tasks indicate that our approach achieves absolute improvements over the strong baseline sys- tems and shows competitive performance on all tasks.

One of the weaknesses of Neural Machine Translation (NMT) is in handling lowfrequency and ambiguous words, which we refer as troublesome words. To address this problem, we propose a novel memoryenhanced NMT method. First, we investigate different strategies to define and detect the troublesome words. Then, a contextual memory is constructed to memorize which target words should be produced in what situations. Finally, we design a hybrid model to dynamically access the contextual memory so as to correctly translate the troublesome words. The extensive experiments on Chinese-to-English and English-to-German translation tasks demonstrate that our method significantly outperforms the strong baseline models in translation quality, especially in handling troublesome words.

In the hierarchical phrase based (HPB) translation model, in addition to hierarchical phrase pairs extracted from bi-text, glue rules are used to perform serial combination of phrases. However, this basic method for combining phrases is not sufficient for phrase reordering. In this paper, we extend the HPB model with maximum entropy based bracketing transduction grammar (BTG), which provides content-dependent combination of neighboring phrases in two ways: serial or inverse. Experimental results show that the extended HPB system achieves absolute improvements of 0.9∼1.8 BLEU points over the baseline for large-scale translation tasks.

This paper presents a description for the ICT systems involved in the IWSLT 2008 evaluation campaign. This year, we participated in Chinese-English and English-Chinese translation directions. Four statistical machine translation systems were used: one linguistically syntax-based, two formally syntax-based, and one phrase-based. The outputs of the four SMT systems were fed to a sentence-level system combiner, which was expected to produce better translations than single systems. We will report the results of the four single systems and the combiner on both the development and test sets.

In this paper, we give an overview of the ICT statistical machine translation systems for the evaluation campaign of the International Workshop on Spoken Language Translation (IWSLT) 2007. In this year’s evaluation, we participated in the Chinese-English transcript translation task, and developed three systems based on different techniques: a formally syntax-based system Bruin, an extended phrase-based system Confucius and a linguistically syntax-based system Lynx. We will describe the models of these three systems, and compare their performance in detail. We set Bruin as our primary system, which ranks 2 among the 15 primary results according to the official evaluation results.