Encoder pre-training is promising in end-to-end Speech Translation (ST), given the fact that speech-to-translation data is scarce. But ST encoders are not simple instances of Automatic Speech Recognition (ASR) or Machine Translation (MT) encoders. For example, we find that ASR encoders lack the global context representation, which is necessary for translation, whereas MT encoders are not designed to deal with long but locally attentive acoustic sequences. In this work, we propose a Stacked Acoustic-and-Textual Encoding (SATE) method for speech translation. Our encoder begins with processing the acoustic sequence as usual, but later behaves more like an MT encoder for a global representation of the input sequence. In this way, it is straightforward to incorporate the pre-trained models into the system. Also, we develop an adaptor module to alleviate the representation inconsistency between the pre-trained ASR encoder and MT encoder, and develop a multi-teacher knowledge distillation method to preserve the pre-training knowledge. Experimental results on the LibriSpeech En-Fr and MuST-C En-De ST tasks show that our method achieves state-of-the-art BLEU scores of 18.3 and 25.2. To our knowledge, we are the first to develop an end-to-end ST system that achieves comparable or even better BLEU performance than the cascaded ST counterpart when large-scale ASR and MT data is available.

This paper proposes a new pre-training method, called Code-Switching Pre-training (CSP for short) for Neural Machine Translation (NMT). Unlike traditional pre-training method which randomly masks some fragments of the input sentence, the proposed CSP randomly replaces some words in the source sentence with their translation words in the target language. Specifically, we firstly perform lexicon induction with unsupervised word embedding mapping between the source and target languages, and then randomly replace some words in the input sentence with their translation words according to the extracted translation lexicons. CSP adopts the encoder-decoder framework: its encoder takes the code-mixed sentence as input, and its decoder predicts the replaced fragment of the input sentence. In this way, CSP is able to pre-train the NMT model by explicitly making the most of the alignment information extracted from the source and target monolingual corpus. Additionally, we relieve the pretrain-finetune discrepancy caused by the artificial symbols like [mask]. To verify the effectiveness of the proposed method, we conduct extensive experiments on unsupervised and supervised NMT. Experimental results show that CSP achieves significant improvements over baselines without pre-training or with other pre-training methods.

Large amounts of data has made neural machine translation (NMT) a big success in recent years. But it is still a challenge if we train these models on small-scale corpora. In this case, the way of using data appears to be more important. Here, we investigate the effective use of training data for low-resource NMT. In particular, we propose a dynamic curriculum learning (DCL) method to reorder training samples in training. Unlike previous work, we do not use a static scoring function for reordering. Instead, the order of training samples is dynamically determined in two ways - loss decline and model competence. This eases training by highlighting easy samples that the current model has enough competence to learn. We test our DCL method in a Transformer-based system. Experimental results show that DCL outperforms several strong baselines on three low-resource machine translation benchmarks and different sized data of WMT’16 En-De.

This paper describes the Neural Machine Translation (NMT) system of TencentFmRD for Chinese↔English news translation tasks of WMT 2018. Our systems are neural machine translation systems trained with our original system TenTrans. TenTrans is an improved NMT system based on Transformer self-attention mechanism. In addition to the basic settings of Transformer training, TenTrans uses multi-model fusion techniques, multiple features reranking, different segmentation models and joint learning. Finally, we adopt some data selection strategies to fine-tune the trained system and achieve a stable performance improvement. Our Chinese→English system achieved the second best BLEU scores and fourth best cased BLEU scores among all WMT18 submitted systems.

Boundary features are widely used in traditional Chinese Word Segmentation (CWS) methods as they can utilize unlabeled data to help improve the Out-of-Vocabulary (OOV) word recognition performance. Although various neural network methods for CWS have achieved performance competitive with state-of-the-art systems, these methods, constrained by the domain and size of the training corpus, do not work well in domain adaptation. In this paper, we propose a novel BLSTM-based neural network model which incorporates a global recurrent structure designed for modeling boundary features dynamically. Experiments show that the proposed structure can effectively boost the performance of Chinese Word Segmentation, especially OOV-Recall, which brings benefits to domain adaptation. We achieved state-of-the-art results on 6 domains of CNKI articles, and competitive results to the best reported on the 4 domains of SIGHAN Bakeoff 2010 data.

Grammatical Error Diagnosis for Chinese has always been a challenge for both foreign learners and NLP researchers, for the variousity of grammar and the flexibility of expression. In this paper, we present a model based on Bidirectional Long Short-Term Memory(Bi-LSTM) neural networks, which treats the task as a sequence labeling problem, so as to detect Chinese grammatical errors, to identify the error types and to locate the error positions. In the corpora of this year’s shared task, there can be multiple errors in a single offset of a sentence, to address which, we simutaneously train three Bi-LSTM models sharing word embeddings which label Missing, Redundant and Selection errors respectively. We regard word ordering error as a special kind of word selection error which is longer during training phase, and then separate them by length during testing phase. In NLP-TEA 3 shared task for Chinese Grammatical Error Diagnosis(CGED), Our system achieved relatively high F1 for all the three levels in the traditional Chinese track and for the detection level in the Simpified Chinese track.