Pre-trained models have drastically changed the field of natural language processing by providing a way to leverage large-scale language representations to various tasks. Some pre-trained models offer general-purpose representations, while others are specialized in particular tasks, like neural machine translation (NMT). Multilingual NMT-targeted systems are often fine-tuned for specific language pairs, but there is a lack of evidence-based best-practice recommendations to guide this process. Moreover, the trend towards even larger pre-trained models has made it challenging to deploy them in the computationally restrictive environments typically found in developing regions where low-resource languages are usually spoken. We propose a pipeline to tune the mBART50 pre-trained model to 8 diverse low-resource language pairs, and then distil the resulting system to obtain lightweight and more sustainable models. Our pipeline conveniently exploits back-translation, synthetic corpus filtering, and knowledge distillation to deliver efficient, yet powerful bilingual translation models 13 times smaller than the original pre-trained ones, but with close performance in terms of BLEU.

Computer-aided translation (CAT) tools based on translation memories (MT) play a prominent role in the translation workflow of professional translators. However, the reduced availability of in-domain TMs, as compared to in-domain monolingual corpora, limits its adoption for a number of translation tasks. In this paper, we introduce a novel neural approach aimed at overcoming this limitation by exploiting not only TMs, but also in-domain target-language (TL) monolingual corpora, and still enabling a similar functionality to that offered by conventional TM-based CAT tools. Our approach relies on cross-lingual sentence embeddings to retrieve translation proposals from TL monolingual corpora, and on a neural model to estimate their post-editing effort. The paper presents an automatic evaluation of these techniques on four language pairs that shows that our approach can successfully exploit monolingual texts in a TM-based CAT environment, increasing the amount of useful translation proposals, and that our neural model for estimating the post-editing effort enables the combination of translation proposals obtained from monolingual corpora and from TMs in the usual way. A human evaluation performed on a single language pair confirms the results of the automatic evaluation and seems to indicate that the translation proposals retrieved with our approach are more useful than what the automatic evaluation shows.

In the context of neural machine translation, data augmentation (DA) techniques may be used for generating additional training samples when the available parallel data are scarce. Many DA approaches aim at expanding the support of the empirical data distribution by generating new sentence pairs that contain infrequent words, thus making it closer to the true data distribution of parallel sentences. In this paper, we propose to follow a completely different approach and present a multi-task DA approach in which we generate new sentence pairs with transformations, such as reversing the order of the target sentence, which produce unfluent target sentences. During training, these augmented sentences are used as auxiliary tasks in a multi-task framework with the aim of providing new contexts where the target prefix is not informative enough to predict the next word. This strengthens the encoder and forces the decoder to pay more attention to the source representations of the encoder. Experiments carried out on six low-resource translation tasks show consistent improvements over the baseline and over DA methods aiming at extending the support of the empirical data distribution. The systems trained with our approach rely more on the source tokens, are more robust against domain shift and suffer less hallucinations.

This paper describes the joint submission of Universitat d’Alacant and Prompsit Language Engineering to the WMT 2020 shared task on parallel corpus filtering. Our submission, based on the free/open-source tool Bicleaner, enhances it with Extremely Randomised Trees and lexical similarity features that account for the frequency of the words in the parallel sentences to determine if two sentences are parallel. To train this classifier we used the clean corpora provided for the task and synthetic noisy parallel sentences. In addition we re-score the output of Bicleaner using character-level language models and n-gram saturation.

Corpus-based approaches to machine translation (MT) have difficulties when the amount of parallel corpora to use for training is scarce, especially if the languages involved in the translation are highly inflected. This problem can be addressed from different perspectives, including data augmentation, transfer learning, and the use of additional resources, such as those used in rule-based MT. This paper focuses on the hybridisation of rule-based MT and neural MT for the Breton–French under-resourced language pair in an attempt to study to what extent the rule-based MT resources help improve the translation quality of the neural MT system for this particular under-resourced language pair. We combine both translation approaches in a multi-source neural MT architecture and find out that, even though the rule-based system has a low performance according to automatic evaluation metrics, using it leads to improved translation quality.

This paper describes our approach to create a neural machine translation system to translate between English and Swahili (both directions) in the news domain, as well as the process we followed to crawl the necessary parallel corpora from the Internet. We report the results of a pilot human evaluation performed by the news media organisations participating in the H2020 EU-funded project GoURMET.

This paper studies the effects of word-level linguistic annotations in under-resourced neural machine translation, for which there is incomplete evidence in the literature. The study covers eight language pairs, different training corpus sizes, two architectures, and three types of annotation: dummy tags (with no linguistic information at all), part-of-speech tags, and morpho-syntactic description tags, which consist of part of speech and morphological features. These linguistic annotations are interleaved in the input or output streams as a single tag placed before each word. In order to measure the performance under each scenario, we use automatic evaluation metrics and perform automatic error classification. Our experiments show that, in general, source-language annotations are helpful and morpho-syntactic descriptions outperform part of speech for some language pairs. On the contrary, when words are annotated in the target language, part-of-speech tags systematically outperform morpho-syntactic description tags in terms of automatic evaluation metrics, even though the use of morpho-syntactic description tags improves the grammaticality of the output. We provide a detailed analysis of the reasons behind this result.

This paper describes the two submissions of Universitat d’Alacant to the English-to-Kazakh news translation task at WMT 2019. Our submissions take advantage of monolingual data and parallel data from other language pairs by means of iterative backtranslation, pivot backtranslation and transfer learning. They also use linguistic information in two ways: morphological segmentation of Kazakh text, and integration of the output of a rule-based machine translation system. Our systems were ranked second in terms of chrF++ despite being built from an ensemble of only 2 independent training runs.

This paper describes Prompsit Language Engineering’s submissions to the WMT 2018 parallel corpus filtering shared task. Our four submissions were based on an automatic classifier for identifying pairs of sentences that are mutual translations. A set of hand-crafted hard rules for discarding sentences with evident flaws were applied before the classifier. We explored different strategies for achieving a training corpus with diverse vocabulary and fluent sentences: language model scoring, an active-learning-inspired data selection algorithm and n-gram saturation. Our submissions were very competitive in comparison with other participants on the 100 million word training corpus.

This paper presents Prompsit Language Engineering’s submission to the IWSLT 2018 Low Resource Machine Translation task. Our submission is based on cross-lingual learning: a multilingual neural machine translation system was created with the sole purpose of improving translation quality on the Basque-to-English language pair. The multilingual system was trained on a combination of in-domain data, pseudo in-domain data obtained via cross-entropy data selection and backtranslated data. We morphologically segmented Basque text with a novel approach that only requires a dictionary such as those used by spell checkers and proved that this segmentation approach outperforms the widespread byte pair encoding strategy for this task.

We aim to shed light on the strengths and weaknesses of the newly introduced neural machine translation paradigm. To that end, we conduct a multifaceted evaluation in which we compare outputs produced by state-of-the-art neural machine translation and phrase-based machine translation systems for 9 language directions across a number of dimensions. Specifically, we measure the similarity of the outputs, their fluency and amount of reordering, the effect of sentence length and performance across different error categories. We find out that translations produced by neural machine translation systems are considerably different, more fluent and more accurate in terms of word order compared to those produced by phrase-based systems. Neural machine translation systems are also more accurate at producing inflected forms, but they perform poorly when translating very long sentences.

In this paper, we describe two methods developed for sharing linguistic data between two free and open source rule based machine translation systems: Apertium, a shallow-transfer system; and Grammatical Framework (GF), which performs a deeper syntactic transfer. In the first method, we describe the conversion of lexical data from Apertium to GF, while in the second one we automatically extract Apertium shallow-transfer rules from a GF bilingual grammar. We evaluated the resulting systems in a English-Spanish translation context, and results showed the usefulness of the resource sharing and confirmed the a-priori strong and weak points of the systems involved.

In this paper, a previous work on the enlargement of monolingual dictionaries of rule-based machine translation systems by non-expert users is extended to tackle the complete task of adding both source-language and target-language words to the monolingual dictionaries and the bilingual dictionary. In the original method, users validate whether some suffix variations of the word to be inserted are correct in order to find the most appropriate inflection paradigm. This method is now improved by taking advantage from the strong correlation detected between paradigms in both languages to reduce the search space of the target-language paradigm once the source-language paradigm is known. Results show that, when the source-language word has already been inserted, the system is able to more accurately predict which is the right target-language paradigm, and the number of queries posed to users is significantly reduced. Experiments also show that, when the source language and the target language are not closely related, it is only the source-language part-of-speech category, but not the rest of information provided by the source-language paradigm, which helps to correctly classify the target-language word.

Softcatala` is a non-profit association created more than 10 years ago to fight the marginalisation of the Catalan language in information and communication technologies. It has led the localisation of many applications and the creation of a website which allows its users to translate texts between Spanish and Catalan using an external closedsource translation engine. Recently, the closed-source translation back-end has been replaced by a free/open-source solution completely managed by Softcatala`: the Apertium machine translation platform and the ScaleMT web service framework. Thanks to the openness of the new solution, it is possible to take advantage of the huge amount of users of the Softcatala` translation service to improve it, using a series of methods presented in this paper. In addition, a study of the translations requested by the users has been carried out, and it shows that the translation back-end change has not affected the usage patterns.

Some machine translation services like Google Ajax Language API have become very popular as they make the collaboratively created contents of the web 2.0 available to speakers of many languages. One of the keys of its success is its clear and easy-to-use application programming interface (API) and a scalable and reliable service. This paper describes a highly scalable implementation of an Apertium-based translation web service, that aims to make contents available to speakers of lesser resourced languages. The API of this service is compatible with Google’s one, and the scalability of the system is achieved by a new architecture that allows adding or removing new servers at any time; for that, an application placement algorithm which decides which language pairs should be translated on which servers is designed. Our experiments show how the resulting architecture improves the translation rate in comparison to existing Apertium-based servers.