Multi-Teacher Distillation With Single Model for Neural Machine Translation

Most dominant neural machine translation (NMT) models are restricted to make predictions only according to the local context of preceding words in a left-to-right manner. Although many previous studies try to incorporate global information into NMT models, there still exist limitations on how to effectively exploit bidirectional global context. In this paper, we propose a Confidence Based Bidirectional Global Context Aware (CBBGCA) training framework for NMT, where the NMT model is jointly trained with an auxiliary conditional masked language model (CMLM). The training consists of two stages: (1) multi-task joint training; (2) confidence based knowledge distillation. At the first stage, by sharing encoder parameters, the NMT model is additionally supervised by the signal from the CMLM decoder that contains bidirectional global contexts. Moreover, at the second stage, using the CMLM as teacher, we further pertinently incorporate bidirectional global context to the NMT model on its unconfidently-predicted target words via knowledge distillation. Experimental results show that our proposed CBBGCA training framework significantly improves the NMT model by +1.02, +1.30 and +0.57 BLEU scores on three large-scale translation datasets, namely WMT'14 English-to-German, WMT'19 Chinese-to-English and WMT'14 English-to-French, respectively.

The dominant neural machine translation (NMT) models that based on the encoder-decoder architecture have recently achieved the state-of-the-art performance. Traditionally, the NMT models only depend on the representations learned during training for mapping a source sentence into the target domain. However, the learned representations often suffer from implicit and inadequately informed properties. In this paper, we propose a novel bilingual topic enhanced NMT (BLTNMT) model to improve translation performance by incorporating bilingual topic knowledge into NMT. Specifically, the bilingual topic knowledge is included into the hidden states of both encoder and decoder, as well as the attention mechanism. With this new setting, the proposed BLT-NMT has access to the background knowledge implied in bilingual topics which is beyond the sequential context, and enables the attention mechanism to attend to topic-level attentions for generating accurate target words during translation. Experimental results show that the proposed model consistently outperforms the traditional RNNsearch and the previous topic-informed NMT on Chinese-English and EnglishGerman translation tasks. We also introduce the bilingual topic knowledge into the newly emerged Transformer base model on English-German translation and achieve a notable improvement.

Recent works have shown that Neural Machine Translation (NMT) models achieve impressive performance, however, questions about understanding the behavior of these models remain unanswered. We investigate the unexpected volatility of NMT models where the input is semantically and syntactically correct. We discover that with trivial modifications of source sentences, we can identify cases where unexpected changes happen in the translation and in the worst case lead to mistranslations. This volatile behavior of translating extremely similar sentences in surprisingly different ways highlights the underlying generalization problem of current NMT models. We find that both RNN and Transformer models display volatile behavior in 26% and 19% of sentence variations, respectively.

In this paper we describe our team's (NICT-5) Neural Machine Translation (NMT) models whose translations were submitted to shared tasks of the 7 th Workshop on Asian Translation.We participated in the Indic language multilingual sub-task as well as the NICT-SAP multilingual multi-domain sub-task.We focused on naive many-to-many NMT models which gave reasonable translation quality despite their simplicity.Our observations are twofold: (a.) Many-to-many models suffer from a lack of consistency where the translation quality for some language pairs is very good but for some others it is terrible when compared against one-to-many and many-toone baselines.(b.) Oversampling smaller corpora does not necessarily give the best translation quality for the language pair associated with that pair.

Neural machine translation (NMT) offers a novel alternative formulation of translation that is potentially simpler than statistical approaches. However to reach competitive performance, NMT models need to be exceedingly large. In this paper we consider applying knowledge distillation approaches (Bucila et al., 2006; Hinton et al., 2015) that have proven successful for reducing the size of neural models in other domains to the problem of NMT. We demonstrate that standard knowledge distillation applied to word-level prediction can be effective for NMT, and also introduce two novel sequence-level versions of knowledge distillation that further improve performance, and somewhat surprisingly, seem to eliminate the need for beam search (even when applied on the original teacher model). Our best student model runs 10 times faster than its state-of-the-art teacher with little loss in performance. It is also significantly better than a baseline model trained without knowledge distillation: by 4.2/1.7 BLEU with greedy decoding/beam search. Applying weight pruning on top of knowledge distillation results in a student model that has 13 times fewer parameters than the original teacher model, with a decrease of 0.4 BLEU.

The hypotactic structural relation between clauses plays an important role in improving the discourse coherence of document-level translation. However, the standard neural machine translation (NMT) models do not explicitly model the hypotactic relationship between clauses, which usually leads to structurally incorrect translations of long and complex sentences. This problem is particularly noticeable on Chinese-to-English translation task of complex sentences due to the grammatical form distinction between English and Chinese. English is rich in grammatical form (e.g. verb morphological changes and subordinating conjunctions) while Chinese is poor in grammatical form. These linguistic phenomena make it a challenge for NMT to learn the hypotactic structure knowledge from Chinese as well as the structure alignment between Chinese and English. To address these issues, we propose to model the hypotactic structure for Chinese-to-English complex sentence translation by introducing hypotactic structure knowledge. Specifically, we annotate and build a hypotactic structure aligned parallel corpus that provides rich hypotactic structure knowledge for NMT. Moreover, we further propose a structure-infused neural framework to combine the hypotactic structure knowledge with the NMT model through two integrating strategies. In particular, we introduce a specific structure-aware loss to encourage the NMT model to better learn the structure knowledge. Experimental results on WMT17, WMT18 and WMT19 Chinese-to-English translation tasks demonstrate the effectiveness of the proposed methods.

This paper proposes an English-Chinese machine translation research method based on transfer learning. First, it expounds the theory of neural machine translation and transfer learning and related technologies. Neural machine translation is discussed, the advantages and disadvantages of various models are introduced, and the transformer neural machine translation model framework is selected. For low-resource Chinese-English parallel corpus and Tibetan-Chinese parallel corpus, 30 million Chinese-English parallel corpora, 100,000 Chinese-English low-resource parallel corpora, and 100,000 Tibetan-Chinese parallel corpora were used to pretrain the transformer machine translation architecture. The decoders are all composed of 6 identical hidden layers, the initialization of the model parameters is done by the transformer uniform distribution, and the model training uses Adam as the optimizer. In the model transfer part, the parameters with the better effect of the pretrained model are transferred to the low-resource Chinese-English and Tibetan-Chinese machine translation model training, so as to achieve the purpose of knowledge transfer. The results show that the model transfer learning of low-resource Chinese-English parallel corpus improves the translation system's translation by 3.97 BLEU values compared with the translation system without transfer learning at 0.34 BLEU values. Model transfer learning on low-resource Tibetan-Chinese parallel corpus increases the BLEU value by 2.64 BLEU compared to the translation system without transfer learning. The neural machine translation system that uses BPE technology for preprocessing plus model transfer learning is compared to the translation system that only performs transfer learning and shows an improved 0.26 BLEU value.It is verified that the transfer learning method proposed in this paper has a certain improvement in the effect of low-resource Chinese-English and Tibetan-Chinese neural machine translation models.

Machine translation is a computer-based translation process that receives a set of words from a particular humanreadable language as input and outputs a second set of words in the intended human-readable language. Machine translation has assisted linguists and sociologists all across the world. A machine translation model may be statistical, rule-based, or based on neural networks. The Neural Machine Translation (NMT) model was introduced in response to the numerous drawbacks of rule- based and statistical-based machine translation models. This study adds a parallel corpus of Assamese and English and develops the NMT system, a transformer model with a self- attention mechanism. For translation from English to Assamese, the system received a higher bilingual evaluation understudy (BLEU) score of 7.6, and for translation from Assamese to English,a BLEU score of 23.2.

Neural machine translation (MT) models obtain state-of-the-art performance while maintaining a simple, end-to-end architecture. However, little is known about what these models learn about source and target languages during the training process.

While neural machine translation (NMT) models achieve success in our daily lives, they show vulnerability to adversarial attacks. Despite being harmful, these attacks also offer benefits for interpreting and enhancing NMT models, thus drawing increased research attention. However, existing studies on adversarial attacks are insufficient in both attacking ability and human imperceptibility due to their sole focus on the scope of language. This paper proposes a novel vision-fused attack (VFA) framework to acquire powerful adversarial text, i.e., more aggressive and stealthy. Regarding the attacking ability, we design the vision-merged solution space enhancement strategy to enlarge the limited semantic solution space, which enables us to search for adversarial candidates with higher attacking ability. For human imperceptibility, we propose the perception-retained adversarial text selection strategy to align the human text-reading mechanism. Thus, the finally selected adversarial text could be more deceptive. Extensive experiments on various models, including large language models (LLMs) like LLaMA and GPT-3.5, strongly support that VFA outperforms the comparisons by large margins (up to 81%/14% improvements on ASR/SSIM).

Weight Saliency search with Semantic Constraint for Neural Machine Translation attacks

Machine translation (MT) models usually translate a text at sentence level by considering isolated sentences, which is based on a strict assumption that the sentences in a text are independent of one another.However, the fact is that the texts at discourse level have properties going beyond individual sentences.These properties reveal texts in the frequency and distribution of words, word senses, referential forms and syntactic structures.Disregarding dependencies across sentences will harm translation quality especially in terms of coherence, cohesion, and consistency.To solve these problems, several approaches have previously been investigated for conventional statistical machine translation (SMT).With the fast growth of neural machine translation (NMT), discourse-level NMT has drawn increasing attention from researchers.In this work, we review major works on addressing discourse related problems for both SMT and NMT models with a survey of recent trends in the fields.

The injury severity classifications generated from the Abbreviated Injury Scale (AIS) provide information that allows for standardized comparisons in the field of trauma injury research. However, the majority of injuries are coded in International Classification of Diseases (ICD) and lack this severity information. A system to predict injury severity classifications from ICD codes would be beneficial as manually coding in AIS can be time-intensive or even impossible for some retrospective cases. It has been previously shown that the encoder-decoder-based neural machine translation (NMT) model is more accurate than a one-to-one mapping of ICD codes to AIS. The objective of this study is to compare the accuracy of two architectures, feedforward neural networks (FFNN) and NMT, in predicting Injury Severity Score (ISS) and ISS ≥16 classification. Both architectures were tested in direct conversion from ICD codes to ISS score and indirect conversion through AIS for a total of four models. Trauma cases from the U.S. National Trauma Data Bank were used to develop and test the four models as the injuries were coded in both ICD and AIS. 2,031,793 trauma cases from 2017-2018 were used to train and validate the models while 1,091,792 cases from 2019 were used to test and compare them. The results showed that indirect conversion through AIS using an NMT was the most accurate in predicting the exact ISS score, followed by direct conversion with FFNN, direct conversion with NMT, and lastly indirect conversion with FFNN, with statistically significant differences in performance on all pairwise comparisons. The rankings were similar when comparing the accuracy of predicting ISS ≥16 classification, however the differences were smaller. The NMT architecture continues to demonstrate notable accuracy in predicting exact ISS scores, but a simpler FFNN approach may be preferred in specific situations, such as if only ISS ≥16 classification is needed or large-scale computational resources are unavailable.

The dominant neural machine translation (NMT) models apply unified attentional encoder-decoder neural networks for translation. Traditionally, the NMT decoders adopt recurrent neural networks (RNNs) to perform translation in a left-to-right manner, leaving the target-side contexts generated from right to left unexploited during translation. In this paper, we equip the conventional attentional encoder-decoder NMT framework with a backward decoder, in order to explore bidirectional decoding for NMT. Attending to the hidden state sequence produced by the encoder, our backward decoder first learns to generate the target-side hidden state sequence from right to left. Then, the forward decoder performs translation in the forward direction, while in each translation prediction timestep, it simultaneously applies two attention models to consider the source-side and reverse target-side hidden states, respectively. With this new architecture, our model is able to fully exploit source- and target-side contexts to improve translation quality altogether. Experimental results on NIST Chinese-English and WMT English-German translation tasks demonstrate that our model achieves substantial improvements over the conventional NMT by 3.14 and 1.38 BLEU points, respectively. The source code of this work can be obtained from https://github.com/DeepLearnXMU/ABDNMT.

In this paper, we describe two systems we developed for the three tracks we have participated in the BEA-2019 GEC Shared Task. We investigate competitive classification models with bi-directional recurrent neural networks (Bi-RNN) and neural machine translation (NMT) models. For different tracks, we use ensemble systems to selectively combine the NMT models, the classification models, and some rules, and demonstrate that an ensemble solution can effectively improve GEC performance over single systems. Our GEC systems ranked the first in the Unrestricted Track, and the third in both the Restricted Track and the Low Resource Track.