Improving Statistical Machine Translation for a Resource-Poor Language Using Related Resource-Rich Languages

Abstract

We propose a novel language-independent approach for improving machine translation for resource-poor languages by exploiting their similarity to resource-rich ones. More precisely, we improve the translation from a resource-poor source language X 1 into a resourcerich language Y given a bi-text containing a limited number of parallel sentences for X 1 -Y and a larger bi-text for X 2 -Y for some resource-rich language X 2 that is closely related to X 1 . This is achieved by taking advantage of the opportunities that vocabulary overlap and similarities between the languages X 1 and X 2 in spelling, word order, and syntax offer:(1) we improve the word alignments for the resource-poor language, (2) we further augment it with additional translation options, and (3) we take care of potential spelling differences through appropriate transliteration. The evaluation for Indonesian→English using Malay and for Spanish→English using Portuguese and pretending Spanish is resource-poor shows an absolute gain of up to 1.35 and 3.37 BLEU points, respectively, which is an improvement over the best rivaling approaches, while using much less additional data. Overall, our method cuts the amount of necessary "real" training data by a factor of 2-5.Recent developments in statistical machine translation (SMT), e.g., the availability of efficient implementations of integrated open-source toolkits like Moses (Koehn, Hoang, Birch,

Multimodal Machine Learning: A Survey and Taxonomy

“…Non-parallel co-learning approaches can help when learning representations, allow for better semantic concept understanding and even perform unseen object recognition. [148] Transfer learning is also possible on non-parallel data and allows to learn better representations through transferring information from a representation built using a data rich or clean modality to a data scarce or noisy modality. This type of trasnfer learning is often achieved by using coordinated multimodal representations (see Section 3.2).…”

Exploring System Combination approaches for Indo-Aryan MT Systems

“…This can be implemented by making the machine learn from various iterations of combining and adjusting the scores accordingly. (Nakov and Ng, 2012) have indeed shown that results show significant deviations associated with different weights assigned to the tables.…”

Machine translation for Arabic dialects (survey)

“…It should be noted that this issue does not arise only in the case of Arabic dialects; it concerns also several other under-resourced languages and many research activities focus on machine translation in the context of under-resourced or non-resourced languages. The main idea of these contributions is exploiting the proximity between an under-resourced language and the closest related resourced language (Cantonese⇒Mandarin (Zhang, 1998), Czech⇒Slovak (Hajič et al, 2000), Turkish⇒Crimean Tatar (Altintas and Cicekli, 2002), Irish⇒Scottish Gaelic (Scannell, 2006), Indonesian⇒English using Malay (Nakov and Ng, 2012) and Standard Austrian German⇒Viennese dialect (Haddow et al, 2013)).…”