scholarly journals Minimizing the Bag-of-Ngrams Difference for Non-Autoregressive Neural Machine Translation

2020 ◽  
Vol 34 (01) ◽  
pp. 198-205
Author(s):  
Chenze Shao ◽  
Jinchao Zhang ◽  
Yang Feng ◽  
Fandong Meng ◽  
Jie Zhou
Keyword(s):  
Machine Translation ◽  
Cross Entropy ◽  
Sequential Dependency ◽  
Weak Correlation ◽  
Neural Machine Translation ◽  
Translation Quality ◽  
Word Level ◽  
Translation Errors ◽  
Training Objective ◽  
Target Side

Non-Autoregressive Neural Machine Translation (NAT) achieves significant decoding speedup through generating target words independently and simultaneously. However, in the context of non-autoregressive translation, the word-level cross-entropy loss cannot model the target-side sequential dependency properly, leading to its weak correlation with the translation quality. As a result, NAT tends to generate influent translations with over-translation and under-translation errors. In this paper, we propose to train NAT to minimize the Bag-of-Ngrams (BoN) difference between the model output and the reference sentence. The bag-of-ngrams training objective is differentiable and can be efficiently calculated, which encourages NAT to capture the target-side sequential dependency and correlates well with the translation quality. We validate our approach on three translation tasks and show that our approach largely outperforms the NAT baseline by about 5.0 BLEU scores on WMT14 En↔De and about 2.5 BLEU scores on WMT16 En↔Ro.

scholarly journals Sequence-Level Training for Non-Autoregressive Neural Machine Translation

2021 ◽  
pp. 1-36
Author(s):  
Chenze Shao ◽  
Yang Feng ◽  
Jinchao Zhang ◽  
Fandong Meng ◽  
Jie Zhou
Keyword(s):  
Machine Translation ◽  
Cross Entropy ◽  
Gradient Estimation ◽  
Neural Machine Translation ◽  
Training Strategy ◽  
Word Generation ◽  
Translation Quality ◽  
Word Level ◽  
Training Objective ◽  
Level Training

Abstract In recent years, Neural Machine Translation (NMT) has achieved notable results in various translation tasks. However, the word-by-word generation manner determined by the autoregressive mechanism leads to high translation latency of the NMT and restricts its low-latency applications. Non-Autoregressive Neural Machine Translation (NAT) removes the autoregressive mechanism and achieves significant decoding speedup through generating target words independently and simultaneously. Nevertheless, NAT still takes the word-level cross-entropy loss as the training objective, which is not optimal because the output of NAT cannot be properly evaluated due to the multimodality problem. In this article, we propose using sequence-level training objectives to train NAT models, which evaluate the NAT outputs as a whole and correlates well with the real translation quality. Firstly, we propose training NAT models to optimize sequence-level evaluation metrics (e.g., BLEU) based on several novel reinforcement algorithms customized for NAT, which outperforms the conventional method by reducing the variance of gradient estimation. Secondly, we introduce a novel training objective for NAT models, which aims to minimize the Bag-of-Ngrams (BoN) difference between the model output and the reference sentence. The BoN training objective is differentiable and can be calculated efficiently without doing any approximations. Finally, we apply a three-stage training strategy to combine these two methods to train the NAT model.We validate our approach on four translation tasks (WMT14 En↔De, WMT16 En↔Ro), which shows that our approach largely outperforms NAT baselines and achieves remarkable performance on all translation tasks. The source code is available at https://github.com/ictnlp/Seq-NAT.

scholarly journals Pre-Reordering for Neural Machine Translation: Helpful or Harmful?

2017 ◽  
Vol 108 (1) ◽  
pp. 171-182 ◽  
Author(s):  
Jinhua Du ◽  
Andy Way
Keyword(s):  
Machine Translation ◽  
Statistical Machine Translation ◽  
Word Class ◽  
Word Embeddings ◽  
Neural Machine Translation ◽  
Parts Of Speech ◽  
Translation Quality ◽  
The Impact ◽  
Japanese English ◽  
Target Side

AbstractPre-reordering, a preprocessing to make the source-side word orders close to those of the target side, has been proven very helpful for statistical machine translation (SMT) in improving translation quality. However, is it the case in neural machine translation (NMT)? In this paper, we firstly investigate the impact of pre-reordered source-side data on NMT, and then propose to incorporate features for the pre-reordering model in SMT as input factors into NMT (factored NMT). The features, namely parts-of-speech (POS), word class and reordered index, are encoded as feature vectors and concatenated to the word embeddings to provide extra knowledge for NMT. Pre-reordering experiments conducted on Japanese↔English and Chinese↔English show that pre-reordering the source-side data for NMT is redundant and NMT models trained on pre-reordered data deteriorate translation performance. However, factored NMT using SMT-based pre-reordering features on Japanese→English and Chinese→English is beneficial and can further improve by 4.48 and 5.89 relative BLEU points, respectively, compared to the baseline NMT system.

scholarly journals Neural Machine Translation with Adequacy-Oriented Learning

2019 ◽  
Vol 33 ◽  
pp. 6618-6625 ◽  
Author(s):  
Xiang Kong ◽  
Zhaopeng Tu ◽  
Shuming Shi ◽  
Eduard Hovy ◽  
Tong Zhang
Keyword(s):  
Machine Translation ◽  
State Of The Art ◽  
Likelihood Estimation ◽  
Neural Machine Translation ◽  
Learning Mechanism ◽  
Translation Quality ◽  
Word Level ◽  
Adversarial Training ◽  
Level Training ◽  
Qualitative Analyses

Although Neural Machine Translation (NMT) models have advanced state-of-the-art performance in machine translation, they face problems like the inadequate translation. We attribute this to that the standard Maximum Likelihood Estimation (MLE) cannot judge the real translation quality due to its several limitations. In this work, we propose an adequacyoriented learning mechanism for NMT by casting translation as a stochastic policy in Reinforcement Learning (RL), where the reward is estimated by explicitly measuring translation adequacy. Benefiting from the sequence-level training of RL strategy and a more accurate reward designed specifically for translation, our model outperforms multiple strong baselines, including (1) standard and coverage-augmented attention models with MLE-based training, and (2) advanced reinforcement and adversarial training strategies with rewards based on both word-level BLEU and character-level CHRF3. Quantitative and qualitative analyses on different language pairs and NMT architectures demonstrate the effectiveness and universality of the proposed approach.

scholarly journals Non-Autoregressive Neural Machine Translation with Enhanced Decoder Input

2019 ◽  
Vol 33 ◽  
pp. 3723-3730 ◽  
Author(s):  
Junliang Guo ◽  
Xu Tan ◽  
Di He ◽  
Tao Qin ◽  
Linli Xu ◽  
...  
Keyword(s):  
Machine Translation ◽  
Experimental Results ◽  
Word Embeddings ◽  
Model Accuracy ◽  
Neural Machine Translation ◽  
Word Level ◽  
Sentence Level ◽  
The Cost ◽  
Target Side

Non-autoregressive translation (NAT) models, which remove the dependence on previous target tokens from the inputs of the decoder, achieve significantly inference speedup but at the cost of inferior accuracy compared to autoregressive translation (AT) models. Previous work shows that the quality of the inputs of the decoder is important and largely impacts the model accuracy. In this paper, we propose two methods to enhance the decoder inputs so as to improve NAT models. The first one directly leverages a phrase table generated by conventional SMT approaches to translate source tokens to target tokens, which are then fed into the decoder as inputs. The second one transforms source-side word embeddings to target-side word embeddings through sentence-level alignment and word-level adversary learning, and then feeds the transformed word embeddings into the decoder as inputs. Experimental results show our method largely outperforms the NAT baseline (Gu et al. 2017) by 5.11 BLEU scores on WMT14 English-German task and 4.72 BLEU scores on WMT16 English-Romanian task.

scholarly journals Context-Aware Neural Machine Translation for Korean Honorific Expressions

Electronics ◽  
2021 ◽  
Vol 10 (13) ◽  
pp. 1589
Author(s):  
Yongkeun Hwang ◽  
Yanghoon Kim ◽  
Kyomin Jung
Keyword(s):  
Machine Translation ◽  
Deep Neural Networks ◽  
Contextual Information ◽  
Context Aware ◽  
Neural Machine Translation ◽  
Translation Quality ◽  
Sentence Level ◽  
Proposed Model ◽  
The Given ◽  
The Relationship

Neural machine translation (NMT) is one of the text generation tasks which has achieved significant improvement with the rise of deep neural networks. However, language-specific problems such as handling the translation of honorifics received little attention. In this paper, we propose a context-aware NMT to promote translation improvements of Korean honorifics. By exploiting the information such as the relationship between speakers from the surrounding sentences, our proposed model effectively manages the use of honorific expressions. Specifically, we utilize a novel encoder architecture that can represent the contextual information of the given input sentences. Furthermore, a context-aware post-editing (CAPE) technique is adopted to refine a set of inconsistent sentence-level honorific translations. To demonstrate the efficacy of the proposed method, honorific-labeled test data is required. Thus, we also design a heuristic that labels Korean sentences to distinguish between honorific and non-honorific styles. Experimental results show that our proposed method outperforms sentence-level NMT baselines both in overall translation quality and honorific translations.

Analyzing Subword Techniques to Improve English to Sinhala Neural Machine Translation

2021 ◽  
pp. 2050017
Author(s):  
Rashmini Naranpanawa ◽  
Ravinga Perera ◽  
Thilakshi Fonseka ◽  
Uthayasanker Thayasivam
Keyword(s):  
Machine Translation ◽  
State Of The Art ◽  
Statistical Machine Translation ◽  
Translation System ◽  
Rare Word ◽  
Neural Machine Translation ◽  
Parallel Corpus ◽  
Low Resource ◽  
Word Level ◽  
Morphologically Rich Languages

Neural machine translation (NMT) is a remarkable approach which performs much better than the Statistical machine translation (SMT) models when there is an abundance of parallel corpus. However, vanilla NMT is primarily based upon word-level with a fixed vocabulary. Therefore, low resource morphologically rich languages such as Sinhala are mostly affected by the out of vocabulary (OOV) and Rare word problems. Recent advancements in subword techniques have opened up opportunities for low resource communities by enabling open vocabulary translation. In this paper, we extend our recently published state-of-the-art EN-SI translation system using the transformer and explore standard subword techniques on top of it to identify which subword approach has a greater effect on English Sinhala language pair. Our models demonstrate that subword segmentation strategies along with the state-of-the-art NMT can perform remarkably when translating English sentences into a rich morphology language regardless of a large parallel corpus.

Improving thai-lao neural machine translation with similarity lexicon

2021 ◽  
pp. 1-10
Author(s):  
Zhiqiang Yu ◽  
Yuxin Huang ◽  
Junjun Guo
Keyword(s):  
Machine Translation ◽  
Semantic Information ◽  
Neural Machine Translation ◽  
Low Resource ◽  
Translation Quality ◽  
Decoder Architecture ◽  
Baseline System ◽  
Input Sentence ◽  
Resource Conditions ◽  
Language Pair

It has been shown that the performance of neural machine translation (NMT) drops starkly in low-resource conditions. Thai-Lao is a typical low-resource language pair of tiny parallel corpus, leading to suboptimal NMT performance on it. However, Thai and Lao have considerable similarities in linguistic morphology and have bilingual lexicon which is relatively easy to obtain. To use this feature, we first build a bilingual similarity lexicon composed of pairs of similar words. Then we propose a novel NMT architecture to leverage the similarity between Thai and Lao. Specifically, besides the prevailing sentence encoder, we introduce an extra similarity lexicon encoder into the conventional encoder-decoder architecture, by which the semantic information carried by the similarity lexicon can be represented. We further provide a simple mechanism in the decoder to balance the information representations delivered from the input sentence and the similarity lexicon. Our approach can fully exploit linguistic similarity carried by the similarity lexicon to improve translation quality. Experimental results demonstrate that our approach achieves significant improvements over the state-of-the-art Transformer baseline system and previous similar works.

scholarly journals Recurrent Stacking of Layers for Compact Neural Machine Translation Models

2019 ◽  
Vol 33 ◽  
pp. 6292-6299 ◽  
Author(s):  
Raj Dabre ◽  
Atsushi Fujita
Keyword(s):  
Machine Translation ◽  
Single Layer ◽  
Training Data ◽  
Neural Machine Translation ◽  
Parallel Corpora ◽  
Translation Quality ◽  
Sequence Generation ◽  
Sequence Modeling ◽  
Back Translation

In encoder-decoder based sequence-to-sequence modeling, the most common practice is to stack a number of recurrent, convolutional, or feed-forward layers in the encoder and decoder. While the addition of each new layer improves the sequence generation quality, this also leads to a significant increase in the number of parameters. In this paper, we propose to share parameters across all layers thereby leading to a recurrently stacked sequence-to-sequence model. We report on an extensive case study on neural machine translation (NMT) using our proposed method, experimenting with a variety of datasets. We empirically show that the translation quality of a model that recurrently stacks a single-layer 6 times, despite its significantly fewer parameters, approaches that of a model that stacks 6 different layers. We also show how our method can benefit from a prevalent way for improving NMT, i.e., extending training data with pseudo-parallel corpora generated by back-translation. We then analyze the effects of recurrently stacked layers by visualizing the attentions of models that use recurrently stacked layers and models that do not. Finally, we explore the limits of parameter sharing where we share even the parameters between the encoder and decoder in addition to recurrent stacking of layers.

Sign in / Sign up

Export Citation Format

Share Document