Recent work has questioned the importance of the Transformer's multi-headed attention for achieving high translation quality. We push further in this direction by developing a "hard-coded" attention variant without any learned parameters. Surprisingly, replacing all learned self-attention heads in the encoder and decoder with fixed, input-agnostic Gaussian distributions minimally impacts BLEU scores across four different language pairs. However, additionally hard-coding cross attention (which connects the decoder to the encoder) significantly lowers BLEU, suggesting that it is more important than self-attention. Much of this BLEU drop can be recovered by adding just a single learned cross attention head to an otherwise hard-coded Transformer. Taken as a whole, our results offer insight into which components of the Transformer are actually important, which we hope will guide future work into the development of simpler and more efficient attention-based models.
University of Science and Technology of China（中国科学技术大学）；Microsoft Research（微软研究院）；Microsoft Research Asia（微软亚洲研究院）
Neural machine translation (NMT) typically adopts the encoder-decoder framework. A good understanding of the characteristics and functionalities of the encoder and decoder can help to explain the pros and cons of the framework, and design better models for NMT. In this work, we conduct an empirical study on the encoder and the decoder in NMT, taking Transformer as an example. We find that 1) the decoder handles an easier task than the encoder in NMT, 2) the decoder is more sensitive to the input noise than the encoder, and 3) the preceding words/tokens in the decoder provide strong conditional…
Attentional sequence-to-sequence models have become the new standard for machine translation, but one challenge of such models is a significant increase in training and decoding cost compared to phrase-based systems. Here, we focus on efficient decoding, with a goal of achieving accuracy close the state-of-the-art in neural machine translation (NMT), while achieving CPU decoding speed/throughput close to that of a phrasal decoder. We approach this problem from two angles: First, we describe several techniques for speeding up an NMT beam search decoder, which obtain a 4.4x speedup over a very e…
DFKI（德国人工智能研究中心）；Saarland University（萨尔大学）；China Mobile Online Services（中国移动在线服务有限公司）；Tianjin University（天津大学）；Global Tone Communication Technology Co., Ltd.（全球语通通信技术有限公司）
The Transformer translation model is based on the multi-head attention mechanism, which can be parallelized easily. The multi-head attention network performs the scaled dot-product attention function in parallel, empowering the model by jointly attending to information from different representation subspaces at different positions. In this paper, we present an approach to learning a hard retrieval attention where an attention head only attends to one token in the sentence rather than all tokens. The matrix multiplication between attention probabilities and the value sequence in the standard sc…
It is well known that translations generated by an excellent document-level neural machine translation (NMT) model are consistent and coherent. However, existing sentence-level evaluation metrics like BLEU can hardly reflect the model's performance at the document level. To tackle this issue, we propose a Discourse Cohesion Evaluation Method (DCoEM) in this paper and contribute a new test suite that considers four cohesive manners (reference, conjunction, substitution, and lexical cohesion) to measure the cohesiveness of document translations. The evaluation results on recent document-level NM…
University of Zurich（苏黎世大学）；University of Edinburgh（爱丁堡大学）
Recent research suggests that neural machine translation achieves parity with professional human translation on the WMT Chinese--English news translation task. We empirically test this claim with alternative evaluation protocols, contrasting the evaluation of single sentences and entire documents. In a pairwise ranking experiment, human raters assessing adequacy and fluency show a stronger preference for human over machine translation when evaluating documents as compared to isolated sentences. Our findings emphasise the need to shift towards document-level evaluation as machine translation im…
Even though sequence-to-sequence neural machine translation (NMT) model have achieved state-of-art performance in the recent fewer years, but it is widely concerned that the recurrent neural network (RNN) units are very hard to capture the long-distance state information, which means RNN can hardly find the feature with long term dependency as the sequence becomes longer. Similarly, convolutional neural network (CNN) is introduced into NMT for speeding recently, however, CNN focus on capturing the local feature of the sequence; To relieve this issue, we incorporate a relation network into the …
Mitsubishi Electric Research Laboratories (MERL)（三菱电机研究实验室（MERL））；Chinese University of Hong Kong（香港中文大学）；Rutgers University（罗格斯大学）
In contrast with previous approaches where information flows only towards deeper layers of a stack, we consider a multi-pass transformer (MPT) architecture in which earlier layers are allowed to process information in light of the output of later layers. To maintain a directed acyclic graph structure, the encoder stack of a transformer is repeated along a new multi-pass dimension, keeping the parameters tied, and information is allowed to proceed unidirectionally both towards deeper layers within an encoder stack and towards any layer of subsequent stacks. We consider both soft (i.e., continuo…
School of Informatics（信息学院）；University of Edinburgh（爱丁堡大学）
Every day, millions of people sacrifice their privacy and browsing habits in exchange for online machine translation. Companies and governments with confidentiality requirements often ban online translation or pay a premium to disable logging. To bring control back to the end user and demonstrate speed, we developed translateLocally. Running locally on a desktop or laptop CPU, translateLocally delivers cloud-like translation speed and quality even on 10 year old hardware. The open-source software is based on Marian and runs on Linux, Windows, and macOS.
Leveraging user-provided translation to constrain NMT has practical significance. Existing methods can be classified into two main categories, namely the use of placeholder tags for lexicon words and the use of hard constraints during decoding. Both methods can hurt translation fidelity for various reasons. We investigate a data augmentation method, making code-switched training data by replacing source phrases with their target translations. Our method does not change the MNT model or decoding algorithm, allowing the model to learn lexicon translations by copying source-side target words. Ext…
Idioms are an important language phenomenon in Chinese, but idiom translation is notoriously hard. Current machine translation models perform poorly on idiom translation, while idioms are sparse in many translation datasets. We present PETCI, a parallel English translation dataset of Chinese idioms, aiming to improve idiom translation by both human and machine. The dataset is built by leveraging human and machine effort. Baseline generation models show unsatisfactory abilities to improve translation, but structure-aware classification models show good performance on distinguishing good transla…
Translate Smart, not Hard: Cascaded Translation Systems with Quality-Aware Deferral
Instituto de Telecomunicações（电信研究所）；Instituto Superior Técnico, Universidade de Lisboa（里斯本大学高级技术学院）；CentraleSupélec, Université Paris-Saclay（巴黎萨克雷大学中央高等电力学院）；Unbabel（Unbabel公司）；ELLIS Unit Lisbon（里斯本ELLIS单元）
针对级联翻译中弃权（不执行）规则设计难题，本文提出用现有 QE 指标决定是否调用大模型，使系统在仅 30%–50% 样本上调用大模型时达到同等性能，并经自动与人工评估验证。
Bhasha-Rupantarika: Algorithm-Hardware Co-design approach for Multilingual Neural Machine Translation
Special Manpower Development Program for Chip to Start-Up (SMDP-C2S)（芯片到初创企业专项人才发展计划（SMDP-C2S））；Ministry of Electronics and Information Technology (MeitY)（电子与信息技术部（MeitY））
We describe a method for training accurate Transformer machine-translation models to run inference using 8-bit integer (INT8) hardware matrix multipliers, as opposed to the more costly single-precision floating-point (FP32) hardware. Unlike previous work, which converted only 85 Transformer matrix multiplications to INT8, leaving 48 out of 133 of them in FP32 because of unacceptable accuracy loss, we convert them all to INT8 without compromising accuracy. Tested on the newstest2014 English-to-German translation task, our INT8 Transformer Base and Transformer Big models yield BLEU scores that a…
University of Melbourne（墨尔本大学）；Monash University（莫纳什大学）
Dealing with the complex word forms in morphologically rich languages is an open problem in language processing, and is particularly important in translation. In contrast to most modern neural systems of translation, which discard the identity for rare words, in this paper we propose several architectures for learning word representations from character and morpheme level word decompositions. We incorporate these representations in a novel machine translation model which jointly learns word alignments and translations via a hard attention mechanism. Evaluating on translating from several morph…
In this research paper, I will elaborate on a method to evaluate machine translation models based on their performance on underlying syntactical phenomena between English and Arabic languages. This method is especially important as such "neural" and "machine learning" are hard to fine-tune and change. Thus, finding a way to evaluate them easily and diversely would greatly help the task of bettering them.
African languages are numerous, complex and low-resourced. The datasets required for machine translation are difficult to discover, and existing research is hard to reproduce. Minimal attention has been given to machine translation for African languages so there is scant research regarding the problems that arise when using machine translation techniques. To begin addressing these problems, we trained models to translate English to five of the official South African languages (Afrikaans, isiZulu, Northern Sotho, Setswana, Xitsonga), making use of modern neural machine translation techniques. T…
The recognition of medical entities from natural language is an ubiquitous problem in the medical field, with applications ranging from medical act coding to the analysis of electronic health data for public health. It is however a complex task usually requiring human expert intervention, thus making it expansive and time consuming. The recent advances in artificial intelligence, specifically the raise of deep learning methods, has enabled computers to make efficient decisions on a number of complex problems, with the notable example of neural sequence models and their powerful applications in…
