scholarly journals Urdu to Punjabi Machine Translation: An Incremental Training Approach

2016 ◽  
Vol 7 (4) ◽  
Author(s):  
Umrinderpal Singh ◽  
Vishal Goyal ◽  
Gurpreet Singh
Keyword(s):  
Machine Translation ◽  
Training Approach ◽  
Incremental Training

scholarly journals From Bilingual to Multilingual Neural Machine Translation by Incremental Training

2019 ◽  
Author(s):  
Carlos Escolano ◽  
Marta R. Costa-jussà ◽  
José A. R. Fonollosa
Keyword(s):  
Machine Translation ◽  
Neural Machine Translation ◽  
Incremental Training

scholarly journals Augmenting Neural Machine Translation through Round-Trip Training Approach

2019 ◽  
Vol 9 (1) ◽  
pp. 268-278 ◽  
Author(s):  
Benyamin Ahmadnia ◽  
Bonnie J. Dorr
Keyword(s):  
Machine Translation ◽  
Training Data ◽  
Training Dataset ◽  
Round Trip ◽  
Neural Machine Translation ◽  
Low Resource ◽  
Translation Quality ◽  
High Resource ◽  
Training Approach ◽  
Language Pair

AbstractThe quality of Neural Machine Translation (NMT), as a data-driven approach, massively depends on quantity, quality and relevance of the training dataset. Such approaches have achieved promising results for bilingually high-resource scenarios but are inadequate for low-resource conditions. Generally, the NMT systems learn from millions of words from bilingual training dataset. However, human labeling process is very costly and time consuming. In this paper, we describe a round-trip training approach to bilingual low-resource NMT that takes advantage of monolingual datasets to address training data bottleneck, thus augmenting translation quality. We conduct detailed experiments on English-Spanish as a high-resource language pair as well as Persian-Spanish as a low-resource language pair. Experimental results show that this competitive approach outperforms the baseline systems and improves translation quality.

scholarly journals AN INCREMENTAL APPROACH TO MSE-BASED FEATURE SELECTION

2006 ◽  
Vol 06 (04) ◽  
pp. 451-471 ◽  
Author(s):  
SHENG-UEI GUAN ◽  
YINAN QI ◽  
CHUNYU BAO
Keyword(s):  
Feature Selection ◽  
Error Rate ◽  
Classification Systems ◽  
Benchmark Problems ◽  
Selection Methods ◽  
Squared Error ◽  
Training Approach ◽  
Ranking Scheme ◽  
Training Cost ◽  
Incremental Training

Feature selection plays an important role in classification systems. Using classifier error rate as the evaluation function, feature selection is integrated with incremental training. A neural network classifier is implemented with an incremental training approach to detect and discard irrelevant features. By learning attributes one after another, our classifier can find directly the attributes that make no contribution to classification. These attributes are marked and considered for removal. Incorporated with a minimum squared error (MSE) based feature ranking scheme, four batch removal methods based on classifier error rate have been developed to discard irrelevant features. These feature selection methods reduce the computational complexity involved in searching among a large number of possible solutions significantly. Experimental results show that our feature selection methods work well on several benchmark problems compared with other feature selection methods. The selected subsets are further validated by a constructive backpropagation (CBP) classifier, which confirms increased classification accuracy and reduced training cost.

scholarly journals Improving Context-Aware Neural Machine Translation with Source-side Monolingual Documents

2021 ◽  
Author(s):  
Linqing Chen ◽  
Junhui Li ◽  
Zhengxian Gong ◽  
Xiangyu Duan ◽  
Boxing Chen ◽  
...  
Keyword(s):  
Machine Translation ◽  
Large Scale ◽  
Context Aware ◽  
Training Task ◽  
Neural Machine Translation ◽  
Parallel Corpora ◽  
Global Context ◽  
Original Sentence ◽  
Training Approach ◽  
Left And Right

Document context-aware machine translation remains challenging due to the lack of large-scale document parallel corpora. To make full use of source-side monolingual documents for context-aware NMT, we propose a Pre-training approach with Global Context (PGC). In particular, we first propose a novel self-supervised pre-training task, which contains two training objectives: (1) reconstructing the original sentence from a corrupted version; (2) generating a gap sentence from its left and right neighbouring sentences. Then we design a universal model for PGC which consists of a global context encoder, a sentence encoder and a decoder, with similar architecture to typical context-aware NMT models. We evaluate the effectiveness and generality of our pre-trained PGC model by adapting it to various downstream context-aware NMT models. Detailed experimentation on four different translation tasks demonstrates that our PGC approach significantly improves the translation performance of context-aware NMT. For example, based on the state-of-the-art SAN model, we achieve an averaged improvement of 1.85 BLEU scores and 1.59 Meteor scores on the four translation tasks.

Factored Statistical Machine Translation for German-English

2018 ◽  
Vol 5 (1) ◽  
pp. 37-45
Author(s):  
Darryl Yunus Sulistyan
Keyword(s):  
Machine Translation ◽  
English Language ◽  
Statistical Machine Translation ◽  
New Model ◽  
Language Pair

Machine Translation is a machine that is going to automatically translate given sentences in a language to other particular language. This paper aims to test the effectiveness of a new model of machine translation which is factored machine translation. We compare the performance of the unfactored system as our baseline compared to the factored model in terms of BLEU score. We test the model in German-English language pair using Europarl corpus. The tools we are using is called MOSES. It is freely downloadable and use. We found, however, that the unfactored model scored over 24 in BLEU and outperforms the factored model which scored below 24 in BLEU for all cases. In terms of words being translated, however, all of factored models outperforms the unfactored model.

Sign in / Sign up

Export Citation Format

Share Document