The Volctrans Machine Translation System for WMT20

This paper describes our VolcTrans system on WMT20 shared news translation task. We participated in 8 translation directions. Our basic systems are based on Transformer, with several variants (wider or deeper Transformers, dynamic convolutions). The final system includes text pre-process, data selection, synthetic data generation, advanced model ensemble, and multilingual pre-training.

LightSeq: A High Performance Inference Library for Sequence Processing and Generation

LightSeq is a high performance inference library for sequence processing and generation implemented in CUDA. To our best knowledge, this is the first open-source inference library which fully supports highly efficient computation of modern NLP models such as BERT, GPT, Transformer, etc. This library is efficient, functional and convenient. A demo usage can be found here: https://github.com/bytedance/lightseq/blob/master/example.

Volctrans Parallel Corpus Filtering System for WMT 2020

In this paper, we describe our submissions to the WMT20 shared task on parallel corpus filtering and alignment for low-resource conditions. The task requires the participants to align potential parallel sentence pairs out of the given document pairs, and score them so that low-quality pairs can be filtered. Our system, Volctrans, is made of two modules, i.e., a mining module and a scoring module. Based on the word alignment model, the mining module adopts an iterative mining strategy to extract latent parallel sentences. In the scoring module, an XLM-based scorer provides scores, followed by reranking mechanisms and ensemble. Our submissions outperform the baseline by 3.x/2.x and 2.x/2.x for km-en and ps-en on From Scratch/Fine-Tune conditions, which is the highest among all submissions.

Capturing Longer Context for Document-level Neural Machine Translation: A Multi-resolutional Approach

Discourse context has been proven useful when translating documents. It is quite a challenge to incorporate long document context in the prevailing neural machine translation models such as Transformer. In this paper, we propose multi-resolutional (MR) Doc2Doc, a method to train a neural sequence-to-sequence model for document-level translation. Our trained model can simultaneously translate sentence by sentence as well as a document as a whole. We evaluate our method and several recent approaches on nine document-level datasets and two sentence-level datasets across six languages. Experiments show that MR Doc2Doc outperforms sentence-level models and previous methods in a comprehensive set of metrics, including BLEU, four lexical indices, three newly proposed assistant linguistic indicators, and human evaluation.

Pre-training Multilingual Neural Machine Translation by Leveraging Alignment Information

We investigate the following question for machine translation (MT): can we develop a single universal MT model to serve as the common seed and obtain derivative and improved models on arbitrary language pairs? We propose mRASP, an approach to pre-train a universal multilingual neural machine translation model. Our key idea in mRASP is its novel technique of random aligned substitution, which brings words and phrases with similar meanings across multiple languages closer in the representation space. We pre-train a mRASP model on 32 language pairs jointly with only public datasets. The model is then fine-tuned on downstream language pairs to obtain specialized MT models. We carry out extensive experiments on 42 translation directions across a diverse settings, including low, medium, rich resource, and as well as transferring to exotic language pairs. Experimental results demonstrate that mRASP achieves significant performance improvement compared to directly training on those target pairs. It is the first time to verify that multiple low-resource language pairs can be utilized to improve rich resource MT. Surprisingly, mRASP is even able to improve the translation quality on exotic languages that never occur in the pre-training corpus. Code, data, and pre-trained models are available at https://github.com/linzehui/mRASP.

SDST: Successive Decoding for Speech-to-text Translation

End-to-end speech-to-text translation (ST), which directly translates the source language speech to the target language text, has attracted intensive attention recently. However, the combination of speech recognition and machine translation in a single model poses a heavy burden on the direct cross-modal cross-lingual mapping. To reduce the learning difficulty, we propose SDST, an integral framework with \textbf{S}uccessive \textbf{D}ecoding for end-to-end \textbf{S}peech-to-text \textbf{T}ranslation task. This method is verified in two mainstream datasets. Experiments show that our proposed \method improves the previous state-of-the-art methods by big margins.

TED: Triple Supervision Decouples End-to-end Speech-to-text Translation

An end-to-end speech-to-text translation (ST) takes audio in a source language and outputs the text in a target language. Inspired by neuroscience, humans have perception systems and cognitive systems to process different information, we propose TED, \textbf{T}ransducer-\textbf{E}ncoder-\textbf{D}ecoder, a unified framework with triple supervision to decouple the end-to-end speech-to-text translation task. In addition to the target sentence translation loss, \method includes two auxiliary supervising signals to guide the acoustic transducer that extracts acoustic features from the input, and the semantic encoder to extract semantic features relevant to the source transcription text. Our method achieves state-of-the-art performance on both English-French and English-German speech translation benchmarks.

Generative Imagination Elevates Machine Translation

There are thousands of languages on earth, but visual perception is shared among peoples. Existing multimodal neural machine translation (MNMT) methods achieve knowledge transfer by enforcing one encoder to learn shared representation across textual and visual modalities. However, the training and inference process heavily relies on well-aligned bilingual sentence - image triplets as input, which are often limited in quantity. In this paper, we hypothesize that visual imagination via synthesizing visual representation from source text could help the neural model map two languages with different symbols, thus helps the translation task. Our proposed end-to-end imagination-based machine translation model (ImagiT) first learns to generate semantic-consistent visual representation from source sentence, and then generate target sentence based on both text representation and imagined visual representation. Experiments demonstrate that our translation model benefits from visual imagination and significantly outperforms the text-only neural machine translation (NMT) baseline. We also conduct analyzing experiments, and the results show that imagination can help fill in missing information when performing the degradation strategy.

Glancing Transformer for Non-Autoregressive Neural Machine Translation

Non-autoregressive neural machine translation achieves remarkable inference acceleration compared to autoregressive models. However, current non-autoregressive models still fall behind their autoregressive counterparts in prediction accuracy. We attribute the accuracy gaps to two disadvantages of non-autoregressive models: a) learning simultaneous generation under the overly strong conditional independence assumption; b) lacking explicit target language modeling. In this paper, we propose Glancing Transformer (GLAT) to address the above disadvantages, which reduces the difficulty of learning simultaneous generation and introduces explicit target language modeling in the non-autoregressive setting at the same time. Experiments on several benchmarks demonstrate that our approach significantly improves the accuracy of non-autoregressive models without sacrificing any inference efficiency. In particular, GLAT achieves 30.91 BLEU on WMT 2014 German-English, which narrows the gap between autoregressive models and non-autoregressive models to less than 0.5 BLEU score.

Improving Maximum Likelihood Training for Text Generation with Density Ratio Estimation

Auto-regressive sequence generative models trained by Maximum Likelihood Estimation suffer the exposure bias problem in practical finite sample scenarios. The crux is that the number of training samples for Maximum Likelihood Estimation is usually limited and the input data distributions are different at training and inference stages. Many method shave been proposed to solve the above problem (Yu et al., 2017; Lu et al., 2018), which relies on sampling from the non-stationary model distribution and suffers from high variance or biased estimations. In this paper, we propose{\psi}-MLE, a new training scheme for auto-regressive sequence generative models, which is effective and stable when operating at large sample space encountered in text generation. We derive our algorithm from a new perspective of self-augmentation and introduce bias correction with density ratio estimation. Extensive experimental results on synthetic data and real-world text generation tasks demonstrate that our method stably outperforms Maximum Likelihood Estimation and other state-of-the-art sequence generative models in terms of both quality and diversity.