For end-to-end speech translation, regularizing the encoder with the Connectionist Temporal Classification (CTC) objective using the source transcript or target translation as labels can greatly improve quality. However, CTC demands an extra prediction layer over the vocabulary space, bringing in non-negligible model parameters and computational overheads, although this layer becomes useless at inference. In this paper, we re-examine the need for genuine vocabulary labels for CTC for regularization and explore strategies to reduce the CTC label space, targeting improved efficiency without quality degradation. We propose coarse labeling for CTC (CoLaCTC), which merges vocabulary labels via simple heuristic rules, such as using truncation, division or modulo (MOD) operations. Despite its simplicity, our experiments on 4 source and 8 target languages show that CoLaCTC with MOD particularly can compress the label space aggressively to 256 and even further, gaining training efficiency (1.18× ∼ 1.77× speedup depending on the original vocabulary size) yet still delivering comparable or better performance than the CTC baseline. We also show that CoLaCTC successfully generalizes to CTC regularization regardless of using transcript or translation for labeling.

In simultaneous translation, the retranslation approach has the advantage of requiring no modifications to the inference engine. However, in order to reduce the undesirable flicker in the output, previous work has resorted to increasing the latency through masking, and introducing specialised inference, thus losing the simplicity of the approach. In this work, we show that self-training improves the flicker-latency tradeoff, while maintaining similar translation quality to the original. Our analysis indicates that self-training reduces flicker by controlling monotonicity. Furthermore, self-training can be combined with biased beam search to further improve the flicker-latency tradeoff.

Document-level neural machine translation (DocNMT) achieves coherent translations by incorporating cross-sentence context. However, for most language pairs there’s a shortage of parallel documents, although parallel sentences are readily available. In this paper, we study whether and how contextual modeling in DocNMT is transferable via multilingual modeling. We focus on the scenario of zero-shot transfer from teacher languages with document level data to student languages with no documents but sentence level data, and for the first time treat document-level translation as a transfer learning problem. Using simple concatenation-based DocNMT, we explore the effect of 3 factors on the transfer: the number of teacher languages with document level data, the balance between document and sentence level data at training, and the data condition of parallel documents (genuine vs. back-translated). Our experiments on Europarl-7 and IWSLT-10 show the feasibility of multilingual transfer for DocNMT, particularly on document-specific metrics. We observe that more teacher languages and adequate data balance both contribute to better transfer quality. Surprisingly, the transfer is less sensitive to the data condition, where multilingual DocNMT delivers decent performance with either back-translated or genuine document pairs.

The machine translation efficiency task challenges participants to make their systems faster and smaller with minimal impact on translation quality. How much quality to sacrifice for efficiency depends upon the application, so participants were encouraged to make multiple submissions covering the space of trade-offs. In total, there were 76 submissions from 5 teams. The task covers GPU, single-core CPU, and multi-core CPU hardware tracks as well as batched throughput or single-sentence latency conditions. Submissions showed hundreds of millions of words can be translated for a dollar, average latency is 3.5–25 ms, and models fit in 7.5–900 MB.

We participated in all tracks of the WMT 2022 efficient machine translation task: single-core CPU, multi-core CPU, and GPU hardware with throughput and latency conditions. Our submissions explores a number of several efficiency strategies: knowledge distillation, a simpler simple recurrent unit (SSRU) decoder with one or two layers, shortlisting, deep encoder, shallow decoder, pruning and bidirectional decoder. For the CPU track, we used quantized 8-bit models. For the GPU track, we used FP16 quantisation. We explored various pruning strategies and combination of one or more of the above methods.

Recently, it has been argued that encoder-decoder models can be made more interpretable by replacing the softmax function in the attention with its sparse variants. In this work, we introduce a novel, simple method for achieving sparsity in attention: we replace the softmax activation with a ReLU, and show that sparsity naturally emerges from such a formulation. Training stability is achieved with layer normalization with either a specialized initialization or an additional gating function. Our model, which we call Rectified Linear Attention (ReLA), is easy to implement and more efficient than previously proposed sparse attention mechanisms. We apply ReLA to the Transformer and conduct experiments on five machine translation tasks. ReLA achieves translation performance comparable to several strong baselines, with training and decoding speed similar to that of the vanilla attention. Our analysis shows that ReLA delivers high sparsity rate and head diversity, and the induced cross attention achieves better accuracy with respect to source-target word alignment than recent sparsified softmax-based models. Intriguingly, ReLA heads also learn to attend to nothing (i.e. ‘switch off’) for some queries, which is not possible with sparsified softmax alternatives.

This paper describes Edinburgh’s submissions to the IWSLT2021 multilingual speech translation (ST) task. We aim at improving multilingual translation and zero-shot performance in the constrained setting (without using any extra training data) through methods that encourage transfer learning and larger capacity modeling with advanced neural components. We build our end-to-end multilingual ST model based on Transformer, integrating techniques including adaptive speech feature selection, language-specific modeling, multi-task learning, deep and big Transformer, sparsified linear attention and root mean square layer normalization. We adopt data augmentation using machine translation models for ST which converts the zero-shot problem into a zero-resource one. Experimental results show that these methods deliver substantial improvements, surpassing the official baseline by > 15 average BLEU and outperforming our cascading system by > 2 average BLEU. Our final submission achieves competitive performance (runner up).

Document-level contextual information has shown benefits to text-based machine translation, but whether and how context helps end-to-end (E2E) speech translation (ST) is still under-studied. We fill this gap through extensive experiments using a simple concatenation-based context-aware ST model, paired with adaptive feature selection on speech encodings for computational efficiency. We investigate several decoding approaches, and introduce in-model ensemble decoding which jointly performs document- and sentence-level translation using the same model. Our results on the MuST-C benchmark with Transformer demonstrate the effectiveness of context to E2E ST. Compared to sentence-level ST, context-aware ST obtains better translation quality (+0.18-2.61 BLEU), improves pronoun and homophone translation, shows better robustness to (artificial) audio segmentation errors, and reduces latency and flicker to deliver higher quality for simultaneous translation.

Due to the great potential in facilitating software development, code generation has attracted increasing attention recently. Generally, dominant models are Seq2Tree models, which convert the input natural language description into a sequence of tree-construction actions corresponding to the pre-order traversal of an Abstract Syntax Tree (AST). However, such a traversal order may not be suitable for handling all multi-branch nodes. In this paper, we propose to equip the Seq2Tree model with a context-based Branch Selector, which is able to dynamically determine optimal expansion orders of branches for multi-branch nodes. Particularly, since the selection of expansion orders is a non-differentiable multi-step operation, we optimize the selector through reinforcement learning, and formulate the reward function as the difference of model losses obtained through different expansion orders. Experimental results and in-depth analysis on several commonly-used datasets demonstrate the effectiveness and generality of our approach. We have released our code at https://github.com/DeepLearnXMU/CG-RL.

We investigate a long-perceived shortcoming in the typical use of BLEU: its reliance on a single reference. Using modern neural paraphrasing techniques, we study whether automatically generating additional *diverse* references can provide better coverage of the space of valid translations and thereby improve its correlation with human judgments. Our experiments on the into-English language directions of the WMT19 metrics task (at both the system and sentence level) show that using paraphrased references does generally improve BLEU, and when it does, the more diverse the better. However, we also show that better results could be achieved if those paraphrases were to specifically target the parts of the space most relevant to the MT outputs being evaluated. Moreover, the gains remain slight even when human paraphrases are used, suggesting inherent limitations to BLEU’s capacity to correctly exploit multiple references. Surprisingly, we also find that adequacy appears to be less important, as shown by the high results of a strong sampling approach, which even beats human paraphrases when used with sentence-level BLEU.

Information in speech signals is not evenly distributed, making it an additional challenge for end-to-end (E2E) speech translation (ST) to learn to focus on informative features. In this paper, we propose adaptive feature selection (AFS) for encoder-decoder based E2E ST. We first pre-train an ASR encoder and apply AFS to dynamically estimate the importance of each encoded speech feature to ASR. A ST encoder, stacked on top of the ASR encoder, then receives the filtered features from the (frozen) ASR encoder. We take L0DROP (Zhang et al., 2020) as the backbone for AFS, and adapt it to sparsify speech features with respect to both temporal and feature dimensions. Results on LibriSpeech EnFr and MuST-C benchmarks show that AFS facilitates learning of ST by pruning out ~84% temporal features, yielding an average translation gain of ~1.3-1.6 BLEU and a decoding speedup of ~1.4x. In particular, AFS reduces the performance gap compared to the cascade baseline, and outperforms it on LibriSpeech En-Fr with a BLEU score of 18.56 (without data augmentation).

Massively multilingual models for neural machine translation (NMT) are theoretically attractive, but often underperform bilingual models and deliver poor zero-shot translations. In this paper, we explore ways to improve them. We argue that multilingual NMT requires stronger modeling capacity to support language pairs with varying typological characteristics, and overcome this bottleneck via language-specific components and deepening NMT architectures. We identify the off-target translation issue (i.e. translating into a wrong target language) as the major source of the inferior zero-shot performance, and propose random online backtranslation to enforce the translation of unseen training language pairs. Experiments on OPUS-100 (a novel multilingual dataset with 100 languages) show that our approach substantially narrows the performance gap with bilingual models in both one-to-many and many-to-many settings, and improves zero-shot performance by ~10 BLEU, approaching conventional pivot-based methods.

Independence assumptions during sequence generation can speed up inference, but parallel generation of highly inter-dependent tokens comes at a cost in quality. Instead of assuming independence between neighbouring tokens (semi-autoregressive decoding, SA), we take inspiration from bidirectional sequence generation and introduce a decoder that generates target words from the left-to-right and right-to-left directions simultaneously. We show that we can easily convert a standard architecture for unidirectional decoding into a bidirectional decoder by simply interleaving the two directions and adapting the word positions and selfattention masks. Our interleaved bidirectional decoder (IBDecoder) retains the model simplicity and training efficiency of the standard Transformer, and on five machine translation tasks and two document summarization tasks, achieves a decoding speedup of ~2x compared to autoregressive decoding with comparable quality. Notably, it outperforms left-to-right SA because the independence assumptions in IBDecoder are more felicitous. To achieve even higher speedups, we explore hybrid models where we either simultaneously predict multiple neighbouring tokens per direction, or perform multi-directional decoding by partitioning the target sequence. These methods achieve speedups to 4x–11x across different tasks at the cost of <1 BLEU or <0.5 ROUGE (on average)

We describe parBLEU, parCHRF++, and parESIM, which augment baseline metrics with automatically generated paraphrases produced by PRISM (Thompson and Post, 2020a), a multilingual neural machine translation system. We build on recent work studying how to improve BLEU by using diverse automatically paraphrased references (Bawden et al., 2020), extending experiments to the multilingual setting for the WMT2020 metrics shared task and for three base metrics. We compare their capacity to exploit up to 100 additional synthetic references. We find that gains are possible when using additional, automatically paraphrased references, although they are not systematic. However, segment-level correlations, particularly into English, are improved for all three metrics and even with higher numbers of paraphrased references.

It has been shown that the performance of neural machine translation (NMT) drops starkly in low-resource conditions, underperforming phrase-based statistical machine translation (PBSMT) and requiring large amounts of auxiliary data to achieve competitive results. In this paper, we re-assess the validity of these results, arguing that they are the result of lack of system adaptation to low-resource settings. We discuss some pitfalls to be aware of when training low-resource NMT systems, and recent techniques that have shown to be especially helpful in low-resource settings, resulting in a set of best practices for low-resource NMT. In our experiments on German–English with different amounts of IWSLT14 training data, we show that, without the use of any auxiliary monolingual or multilingual data, an optimized NMT system can outperform PBSMT with far less data than previously claimed. We also apply these techniques to a low-resource Korean–English dataset, surpassing previously reported results by 4 BLEU.

Recurrent networks have achieved great success on various sequential tasks with the assistance of complex recurrent units, but suffer from severe computational inefficiency due to weak parallelization. One direction to alleviate this issue is to shift heavy computations outside the recurrence. In this paper, we propose a lightweight recurrent network, or LRN. LRN uses input and forget gates to handle long-range dependencies as well as gradient vanishing and explosion, with all parameter related calculations factored outside the recurrence. The recurrence in LRN only manipulates the weight assigned to each token, tightly connecting LRN with self-attention networks. We apply LRN as a drop-in replacement of existing recurrent units in several neural sequential models. Extensive experiments on six NLP tasks show that LRN yields the best running efficiency with little or no loss in model performance.

The general trend in NLP is towards increasing model capacity and performance via deeper neural networks. However, simply stacking more layers of the popular Transformer architecture for machine translation results in poor convergence and high computational overhead. Our empirical analysis suggests that convergence is poor due to gradient vanishing caused by the interaction between residual connection and layer normalization. We propose depth-scaled initialization (DS-Init), which decreases parameter variance at the initialization stage, and reduces output variance of residual connections so as to ease gradient back-propagation through normalization layers. To address computational cost, we propose a merged attention sublayer (MAtt) which combines a simplified average-based self-attention sublayer and the encoder-decoder attention sublayer on the decoder side. Results on WMT and IWSLT translation tasks with five translation directions show that deep Transformers with DS-Init and MAtt can substantially outperform their base counterpart in terms of BLEU (+1.1 BLEU on average for 12-layer models), while matching the decoding speed of the baseline model thanks to the efficiency improvements of MAtt. Source code for reproduction will be released soon.

With parallelizable attention networks, the neural Transformer is very fast to train. However, due to the auto-regressive architecture and self-attention in the decoder, the decoding procedure becomes slow. To alleviate this issue, we propose an average attention network as an alternative to the self-attention network in the decoder of the neural Transformer. The average attention network consists of two layers, with an average layer that models dependencies on previous positions and a gating layer that is stacked over the average layer to enhance the expressiveness of the proposed attention network. We apply this network on the decoder part of the neural Transformer to replace the original target-side self-attention model. With masking tricks and dynamic programming, our model enables the neural Transformer to decode sentences over four times faster than its original version with almost no loss in training time and translation performance. We conduct a series of experiments on WMT17 translation tasks, where on 6 different language pairs, we obtain robust and consistent speed-ups in decoding.

In this paper, we propose an additionsubtraction twin-gated recurrent network (ATR) to simplify neural machine translation. The recurrent units of ATR are heavily simplified to have the smallest number of weight matrices among units of all existing gated RNNs. With the simple addition and subtraction operation, we introduce a twin-gated mechanism to build input and forget gates which are highly correlated. Despite this simplification, the essential non-linearities and capability of modeling long-distance dependencies are preserved. Additionally, the proposed ATR is more transparent than LSTM/GRU due to the simplification. Forward self-attention can be easily established in ATR, which makes the proposed network interpretable. Experiments on WMT14 translation tasks demonstrate that ATR-based neural machine translation can yield competitive performance on English-German and English-French language pairs in terms of both translation quality and speed. Further experiments on NIST Chinese-English translation, natural language inference and Chinese word segmentation verify the generality and applicability of ATR on different natural language processing tasks.

Parallel sentence representations are important for bilingual and cross-lingual tasks in natural language processing. In this paper, we explore a bilingual autoencoder approach to model parallel sentences. We extract sentence-level global descriptors (e.g. min, max) from word embeddings, and construct two monolingual autoencoders over these descriptors on the source and target language. In order to tightly connect the two autoencoders with bilingual correspondences, we force them to share the same decoding parameters and minimize a corpus-level semantic distance between the two languages. Being optimized towards a joint objective function of reconstruction and semantic errors, our bilingual antoencoder is able to learn continuous-valued latent representations for parallel sentences. Experiments on both intrinsic and extrinsic evaluations on statistical machine translation tasks show that our autoencoder achieves substantial improvements over the baselines.

Estimating similarities at different levels of linguistic units, such as words, sub-phrases and phrases, is helpful for measuring semantic similarity of an entire bilingual phrase. In this paper, we propose a convolution-enhanced bilingual recursive neural network (ConvBRNN), which not only exploits word alignments to guide the generation of phrase structures but also integrates multiple-level information of the generated phrase structures into bilingual semantic modeling. In order to accurately learn the semantic hierarchy of a bilingual phrase, we develop a recursive neural network to constrain the learned bilingual phrase structures to be consistent with word alignments. Upon the generated source and target phrase structures, we stack a convolutional neural network to integrate vector representations of linguistic units on the structures into bilingual phrase embeddings. After that, we fully incorporate information of different linguistic units into a bilinear semantic similarity model. We introduce two max-margin losses to train the ConvBRNN model: one for the phrase structure inference and the other for the semantic similarity model. Experiments on NIST Chinese-English translation tasks demonstrate the high quality of the generated bilingual phrase structures with respect to word alignments and the effectiveness of learned semantic similarities on machine translation.