scholarly journals Multilingual Denoising Pre-training for Neural Machine Translation

2020 ◽  
Vol 8 ◽  
pp. 726-742
Author(s):  
Yinhan Liu ◽  
Jiatao Gu ◽  
Naman Goyal ◽  
Xian Li ◽  
Sergey Edunov ◽  
...  
Keyword(s):  
Machine Translation ◽  
Large Scale ◽  
Complete Sequence ◽  
Neural Machine Translation ◽  
Training Corpus ◽  
Sentence Level ◽  
Significant Performance ◽  
Performance Gains ◽  
Multiple Languages ◽  
Document Level

This paper demonstrates that multilingual denoising pre-training produces significant performance gains across a wide variety of machine translation (MT) tasks. We present mBART—a sequence-to-sequence denoising auto-encoder pre-trained on large-scale monolingual corpora in many languages using the BART objective (Lewis et al., 2019 ). mBART is the first method for pre-training a complete sequence-to-sequence model by denoising full texts in multiple languages, whereas previous approaches have focused only on the encoder, decoder, or reconstructing parts of the text. Pre-training a complete model allows it to be directly fine-tuned for supervised (both sentence-level and document-level) and unsupervised machine translation, with no task- specific modifications. We demonstrate that adding mBART initialization produces performance gains in all but the highest-resource settings, including up to 12 BLEU points for low resource MT and over 5 BLEU points for many document-level and unsupervised models. We also show that it enables transfer to language pairs with no bi-text or that were not in the pre-training corpus, and present extensive analysis of which factors contribute the most to effective pre-training. 1

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 From Words to Sentences: A Progressive Learning Approach for Zero-resource Machine Translation with Visual Pivots

2019 ◽  
Author(s):  
Shizhe Chen ◽  
Qin Jin ◽  
Jianlong Fu
Keyword(s):  
Machine Translation ◽  
Large Scale ◽  
Learning Approach ◽  
Model Learning ◽  
Neural Machine Translation ◽  
Parallel Corpora ◽  
Translation Model ◽  
Word Level ◽  
Sentence Level ◽  
Progressive Learning

The neural machine translation model has suffered from the lack of large-scale parallel corpora. In contrast, we humans can learn multi-lingual translations even without parallel texts by referring our languages to the external world. To mimic such human learning behavior, we employ images as pivots to enable zero-resource translation learning. However, a picture tells a thousand words, which makes multi-lingual sentences pivoted by the same image noisy as mutual translations and thus hinders the translation model learning. In this work, we propose a progressive learning approach for image-pivoted zero-resource machine translation. Since words are less diverse when grounded in the image, we first learn word-level translation with image pivots, and then progress to learn the sentence-level translation by utilizing the learned word translation to suppress noises in image-pivoted multi-lingual sentences. Experimental results on two widely used image-pivot translation datasets, IAPR-TC12 and Multi30k, show that the proposed approach significantly outperforms other state-of-the-art methods.

scholarly journals Towards Making the Most of Context in Neural Machine Translation

2020 ◽  
Author(s):  
Zaixiang Zheng ◽  
Xiang Yue ◽  
Shujian Huang ◽  
Jiajun Chen ◽  
Alexandra Birch
Keyword(s):  
Machine Translation ◽  
State Of The Art ◽  
Local Context ◽  
Unified Approach ◽  
Neural Machine Translation ◽  
Global Context ◽  
Level Data ◽  
Sentence Level ◽  
Target Languages ◽  
Document Level

Document-level machine translation manages to outperform sentence level models by a small margin, but have failed to be widely adopted. We argue that previous research did not make a clear use of the global context, and propose a new document-level NMT framework that deliberately models the local context of each sentence with the awareness of the global context of the document in both source and target languages. We specifically design the model to be able to deal with documents containing any number of sentences, including single sentences. This unified approach allows our model to be trained elegantly on standard datasets without needing to train on sentence and document level data separately. Experimental results demonstrate that our model outperforms Transformer baselines and previous document-level NMT models with substantial margins of up to 2.1 BLEU on state-of-the-art baselines. We also provide analyses which show the benefit of context far beyond the neighboring two or three sentences, which previous studies have typically incorporated.

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 Using Word Embeddings to Enforce Document-Level Lexical Consistency in Machine Translation

2017 ◽  
Vol 108 (1) ◽  
pp. 85-96 ◽  
Author(s):  
Eva Martínez Garcia ◽  
Carles Creus ◽  
Cristina España-Bonet ◽  
Lluís Màrquez
Keyword(s):  
Machine Translation ◽  
Evaluation Metrics ◽  
Automatic Evaluation ◽  
Word Embeddings ◽  
Standard Document ◽  
Sentence Level ◽  
Word Translation ◽  
Stochastic Mechanism ◽  
Document Level

Abstract We integrate new mechanisms in a document-level machine translation decoder to improve the lexical consistency of document translations. First, we develop a document-level feature designed to score the lexical consistency of a translation. This feature, which applies to words that have been translated into different forms within the document, uses word embeddings to measure the adequacy of each word translation given its context. Second, we extend the decoder with a new stochastic mechanism that, at translation time, allows to introduce changes in the translation oriented to improve its lexical consistency. We evaluate our system on English–Spanish document translation, and we conduct automatic and manual assessments of its quality. The automatic evaluation metrics, applied mainly at sentence level, do not reflect significant variations. On the contrary, the manual evaluation shows that the system dealing with lexical consistency is preferred over both a standard sentence-level and a standard document-level phrase-based MT systems.

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.

scholarly journals A Joint Back-Translation and Transfer Learning Method for Low-Resource Neural Machine Translation

2020 ◽  
Vol 2020 ◽  
pp. 1-11
Author(s):  
Gong-Xu Luo ◽  
Ya-Ting Yang ◽  
Rui Dong ◽  
Yan-Hong Chen ◽  
Wen-Bo Zhang
Keyword(s):  
Machine Translation ◽  
Transfer Learning ◽  
Large Scale ◽  
Data Augmentation ◽  
Training Methods ◽  
Learning Method ◽  
Neural Machine Translation ◽  
Low Resource ◽  
Parallel Data ◽  
Back Translation

Neural machine translation (NMT) for low-resource languages has drawn great attention in recent years. In this paper, we propose a joint back-translation and transfer learning method for low-resource languages. It is widely recognized that data augmentation methods and transfer learning methods are both straight forward and effective ways for low-resource problems. However, existing methods, which utilize one of these methods alone, limit the capacity of NMT models for low-resource problems. In order to make full use of the advantages of existing methods and further improve the translation performance of low-resource languages, we propose a new method to perfectly integrate the back-translation method with mainstream transfer learning architectures, which can not only initialize the NMT model by transferring parameters of the pretrained models, but also generate synthetic parallel data by translating large-scale monolingual data of the target side to boost the fluency of translations. We conduct experiments to explore the effectiveness of the joint method by incorporating back-translation into the parent-child and the hierarchical transfer learning architecture. In addition, different preprocessing and training methods are explored to get better performance. Experimental results on Uygur-Chinese and Turkish-English translation demonstrate the superiority of the proposed method over the baselines that use single methods.

scholarly journals A Generic Data-Driven Recommendation System for Large-Scale Regular and Ride-Hailing Taxi Services

Electronics ◽  
2020 ◽  
Vol 9 (4) ◽  
pp. 648 ◽  
Author(s):  
Xiangpeng Wan ◽  
Hakim Ghazzai ◽  
Yehia Massoud
Keyword(s):  
Waiting Time ◽  
Large Scale ◽  
Recommendation System ◽  
Performance Metrics ◽  
Routing Algorithm ◽  
Area Of Interest ◽  
The Future ◽  
Taxi Service ◽  
Significant Performance ◽  
Performance Gains

Modern taxi services are usually classified into two major categories: traditional taxicabs and ride-hailing services. For both services, it is required to design highly efficient recommendation systems to satisfy passengers’ quality of experience and drivers’ benefits. Customers desire to minimize their waiting time before rides, while drivers aim to speed up their customer hunting. In this paper, we propose to leverage taxi service efficiency by designing a generic and smart recommendation system that exploits the benefits of Vehicular Social Networks (VSNs). Aiming at optimizing three key performance metrics, number of pick-ups, customer waiting time, and vacant traveled distance for both taxi services, the proposed recommendation system starts by efficiently estimating the future customer demands in different clusters of the area of interest. Then, it proposes an optimal taxi-to-region matching according to the location of each taxi and the future requested demand of each region. Finally, an optimized geo-routing algorithm is developed to minimize the navigation time spent by drivers. Our simulation model is applied to the borough of Manhattan and is validated with realistic data. Selected results show that significant performance gains are achieved thanks to the additional cooperation among taxi drivers enabled by VSN, as compared to traditional cases.

scholarly journals Identifying Semantics in Clinical Reports Using Neural Machine Translation

2019 ◽  
Vol 33 ◽  
pp. 9552-9557
Author(s):  
Srikanth Mujjiga ◽  
Vamsi Krishna ◽  
Kalyan Chakravarthi ◽  
Vijayananda J
Keyword(s):  
Machine Translation ◽  
Large Scale ◽  
Language Translation ◽  
Semantic Search ◽  
Neural Machine Translation ◽  
Healthcare Facilities ◽  
Semantic Level ◽  
Concept Space ◽  
Unique Approach ◽  
Retrieval Problem

Clinical documents are vital resources for radiologists when they have to consult or refer while studying similar cases. In large healthcare facilities where millions of reports are generated, searching for relevant documents is quite challenging. With abundant interchangeable words in clinical domain, understanding the semantics of the words in the clinical documents is vital to improve the search results. This paper details an end to end semantic search application to address the large scale information retrieval problem of clinical reports. The paper specifically focuses on the challenge of identifying semantics in the clinical reports to facilitate search at semantic level. The semantic search works by mapping the documents into the concept space and the search is performed in the concept space. A unique approach of framing the concept mapping problem as a language translation problem is proposed in this paper. The concept mapper is modelled using the Neural machine translation model (NMT) based on encoder-decoder with attention architecture. The regular expression based concept mapper takes approximately 3 seconds to extract UMLS concepts from a single document, where as the trained NMT does the same in approximately 30 milliseconds. NMT based model further enables incorporation of negation detection to identify whether a concept is negated or not, facilitating search for negated queries.

Sign in / Sign up

Export Citation Format

Share Document