scholarly journals The Suboptimal WMT Test Sets and Its Impact on Human Parity

2021 ◽  
Author(s):  
Ahrii Kim ◽  
Yunju Bak ◽  
Jimin Sun ◽  
Sungwon Lyu ◽  
Changmin Lee
Keyword(s):  
Machine Translation ◽  
Web Crawling ◽  
Data Set ◽  
Test Set ◽  
Neural Machine Translation ◽  
Sentence Level ◽  
Test Sets ◽  
Source Test

With the advent of Neural Machine Translation, the more the achievement of human-machine parity is claimed at WMT, the more we come to ask ourselves if their evaluation environment can be trusted. In this paper, we argue that the low quality of the source test set of the news track at WMT may lead to an overrated human parity claim. First of all, we report nine types of so-called technical contaminants in the data set, originated from an absence of meticulous inspection after web-crawling. Our empirical findings show that when they are corrected, about 5% of the segments that have previously achieved a human parity claim turn out to be statistically invalid. Such a tendency gets evident when the contaminated sentences are solely concerned. To the best of our knowledge, it is the first attempt to question the “source” side of the test set as a potential cause of the overclaim of human parity. We cast evidence for such phenomenon that according to sentence-level TER scores, those trivial errors change a good part of system translations. We conclude that to overlook it would be a mistake, especially when it comes to an NMT evaluation.

Enhancing Lexical Translation Consistency for Document-Level Neural Machine Translation

2022 ◽  
Vol 21 (3) ◽  
pp. 1-21
Author(s):  
Xiaomian Kang ◽  
Yang Zhao ◽  
Jiajun Zhang ◽  
Chengqing Zong
Keyword(s):  
Machine Translation ◽  
English Translation ◽  
Test Set ◽  
Neural Machine Translation ◽  
Global Context ◽  
Translation Quality ◽  
Sentence Level ◽  
Document Level

Document-level neural machine translation (DocNMT) has yielded attractive improvements. In this article, we systematically analyze the discourse phenomena in Chinese-to-English translation, and focus on the most obvious ones, namely lexical translation consistency. To alleviate the lexical inconsistency, we propose an effective approach that is aware of the words which need to be translated consistently and constrains the model to produce more consistent translations. Specifically, we first introduce a global context extractor to extract the document context and consistency context, respectively. Then, the two types of global context are integrated into a encoder enhancer and a decoder enhancer to improve the lexical translation consistency. We create a test set to evaluate the lexical consistency automatically. Experiments demonstrate that our approach can significantly alleviate the lexical translation inconsistency. In addition, our approach can also substantially improve the translation quality compared to sentence-level Transformer.

scholarly journals Transductive Ensemble Learning for Neural Machine Translation

2020 ◽  
Vol 34 (04) ◽  
pp. 6291-6298
Author(s):  
Yiren Wang ◽  
Lijun Wu ◽  
Yingce Xia ◽  
Tao Qin ◽  
ChengXiang Zhai ◽  
...  
Keyword(s):  
Machine Translation ◽  
Ensemble Learning ◽  
State Of The Art ◽  
Ensemble Methods ◽  
Target Language ◽  
Test Set ◽  
Neural Machine Translation ◽  
Learning Tasks ◽  
Marginal Improvement ◽  
Source Test

Ensemble learning, which aggregates multiple diverse models for inference, is a common practice to improve the accuracy of machine learning tasks. However, it has been observed that the conventional ensemble methods only bring marginal improvement for neural machine translation (NMT) when individual models are strong or there are a large number of individual models. In this paper, we study how to effectively aggregate multiple NMT models under the transductive setting where the source sentences of the test set are known. We propose a simple yet effective approach named transductive ensemble learning (TEL), in which we use all individual models to translate the source test set into the target language space and then finetune a strong model on the translated synthetic corpus. We conduct extensive experiments on different settings (with/without monolingual data) and different language pairs (English↔{German, Finnish}). The results show that our approach boosts strong individual models with significant improvement and benefits a lot from more individual models. Specifically, we achieve the state-of-the-art performances on the WMT2016-2018 English↔German translations.

scholarly journals Improving Context-Aware Neural Machine Translation Using Self-Attentive Sentence Embedding

2020 ◽  
Vol 34 (05) ◽  
pp. 9498-9506 ◽  
Author(s):  
Hyeongu Yun ◽  
Yongkeun Hwang ◽  
Kyomin Jung
Keyword(s):  
Machine Translation ◽  
Contextual Information ◽  
Context Aware ◽  
Pronoun Resolution ◽  
Test Set ◽  
Neural Machine Translation ◽  
Attentional Networks ◽  
Multiple Context ◽  
Sentence Level ◽  
Level Information

Fully Attentional Networks (FAN) like Transformer (Vaswani et al. 2017) has shown superior results in Neural Machine Translation (NMT) tasks and has become a solid baseline for translation tasks. More recent studies also have reported experimental results that additional contextual sentences improve translation qualities of NMT models (Voita et al. 2018; Müller et al. 2018; Zhang et al. 2018). However, those studies have exploited multiple context sentences as a single long concatenated sentence, that may cause the models to suffer from inefficient computational complexities and long-range dependencies. In this paper, we propose Hierarchical Context Encoder (HCE) that is able to exploit multiple context sentences separately using the hierarchical FAN structure. Our proposed encoder first abstracts sentence-level information from preceding sentences in a self-attentive way, and then hierarchically encodes context-level information. Through extensive experiments, we observe that our HCE records the best performance measured in BLEU score on English-German, English-Turkish, and English-Korean corpus. In addition, we observe that our HCE records the best performance in a crowd-sourced test set which is designed to evaluate how well an encoder can exploit contextual information. Finally, evaluation on English-Korean pronoun resolution test suite also shows that our HCE can properly exploit contextual information.

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.

scholarly journals The Development of a Comprehensive Data Set for Systematic Studies of Machine Translation

2021 ◽  
pp. 248-262
Author(s):  
Jörg Tiedemann
Keyword(s):  
Machine Translation ◽  
Training Data ◽  
Sufficient Information ◽  
Data Set ◽  
Neural Machine Translation ◽  
High Resource ◽  
Language Groups ◽  
Comprehensive Data ◽  
Parallel Data ◽  
Initial Results

This paper presents our on-going efforts to develop a comprehensive data set and benchmark for machine translation beyond high-resource languages. The current release includes 500GB of compressed parallel data for almost 3,000 language pairs covering over 500 languages and language variants. We present the structure of the data set and demonstrate its use for systematic studies based on baseline experiments with multilingual neural machine translation between Finno-Ugric languages and other language groups. Our initial results show the capabilities of training effective multilingual translation models with skewed training data but also stress the shortcomings with low-resource settings and the difficulties to obtain sufficient information through straightforward transfer from related languages.

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.

scholarly journals Knowledge Graphs Enhanced Neural Machine Translation

2020 ◽  
Author(s):  
Yang Zhao ◽  
Jiajun Zhang ◽  
Yu Zhou ◽  
Chengqing Zong
Keyword(s):  
Machine Translation ◽  
Semantic Space ◽  
Neural Machine Translation ◽  
Translation Quality ◽  
Structured Information ◽  
Knowledge Graphs ◽  
Japanese Translation

Knowledge graphs (KGs) store much structured information on various entities, many of which are not covered by the parallel sentence pairs of neural machine translation (NMT). To improve the translation quality of these entities, in this paper we propose a novel KGs enhanced NMT method. Specifically, we first induce the new translation results of these entities by transforming the source and target KGs into a unified semantic space. We then generate adequate pseudo parallel sentence pairs that contain these induced entity pairs. Finally, NMT model is jointly trained by the original and pseudo sentence pairs. The extensive experiments on Chinese-to-English and Englishto-Japanese translation tasks demonstrate that our method significantly outperforms the strong baseline models in translation quality, especially in handling the induced entities.

scholarly journals Efficient Context-Aware Neural Machine Translation with Layer-Wise Weighting and Input-Aware Gating

2020 ◽  
Author(s):  
Hongfei Xu ◽  
Deyi Xiong ◽  
Josef van Genabith ◽  
Qiuhui Liu
Keyword(s):  
Machine Translation ◽  
Contextual Information ◽  
Computational Cost ◽  
Representation Learning ◽  
Vital Role ◽  
Context Aware ◽  
Neural Machine Translation ◽  
Gating Mechanism ◽  
Sentence Level ◽  
Parallel Data

Existing Neural Machine Translation (NMT) systems are generally trained on a large amount of sentence-level parallel data, and during prediction sentences are independently translated, ignoring cross-sentence contextual information. This leads to inconsistency between translated sentences. In order to address this issue, context-aware models have been proposed. However, document-level parallel data constitutes only a small part of the parallel data available, and many approaches build context-aware models based on a pre-trained frozen sentence-level translation model in a two-step training manner. The computational cost of these approaches is usually high. In this paper, we propose to make the most of layers pre-trained on sentence-level data in contextual representation learning, reusing representations from the sentence-level Transformer and significantly reducing the cost of incorporating contexts in translation. We find that representations from shallow layers of a pre-trained sentence-level encoder play a vital role in source context encoding, and propose to perform source context encoding upon weighted combinations of pre-trained encoder layers' outputs. Instead of separately performing source context and input encoding, we propose to iteratively and jointly encode the source input and its contexts and to generate input-aware context representations with a cross-attention layer and a gating mechanism, which resets irrelevant information in context encoding. Our context-aware Transformer model outperforms the recent CADec [Voita et al., 2019c] on the English-Russian subtitle data and is about twice as fast in training and decoding.

Estimating Machine Translation Quality of Any Input Sentence

2020 ◽  
Vol 30 (01) ◽  
pp. 2050002
Author(s):  
Taichi Aida ◽  
Kazuhide Yamamoto
Keyword(s):  
Machine Translation ◽  
Evaluation Model ◽  
Joint Probability ◽  
Translation System ◽  
Neural Machine Translation ◽  
Translation Quality ◽  
Machine Translation System ◽  
Input Sentence ◽  
The One

Current methods of neural machine translation may generate sentences with different levels of quality. Methods for automatically evaluating translation output from machine translation can be broadly classified into two types: a method that uses human post-edited translations for training an evaluation model, and a method that uses a reference translation that is the correct answer during evaluation. On the one hand, it is difficult to prepare post-edited translations because it is necessary to tag each word in comparison with the original translated sentences. On the other hand, users who actually employ the machine translation system do not have a correct reference translation. Therefore, we propose a method that trains the evaluation model without using human post-edited sentences and in the test set, estimates the quality of output sentences without using reference translations. We define some indices and predict the quality of translations with a regression model. For the quality of the translated sentences, we employ the BLEU score calculated from the number of word [Formula: see text]-gram matches between the translated sentence and the reference translation. After that, we compute the correlation between quality scores predicted by our method and BLEU actually computed from references. According to the experimental results, the correlation with BLEU is the highest when XGBoost uses all the indices. Moreover, looking at each index, we find that the sentence log-likelihood and the model uncertainty, which are based on the joint probability of generating the translated sentence, are important in BLEU estimation.

Sign in / Sign up

Export Citation Format

Share Document