Andy Way

Dublin City University | DCU · School of Computing

This chapter explores the historical timeline of approaches to Sign Language Machine Translation (MT) over the past 25 years. Initially, such approaches were rule-based, but given advances in corpus-based approaches to MT on spoken languages, unsurprisingly researchers started to explore the possibilities for using example-based and statistical met...

In an evolving landscape of crisis communication, the need for robust and adaptable Machine Translation (MT) systems is more pressing than ever, particularly for low-resource languages. This study presents a comprehensive exploration of leveraging Large Language Models (LLMs) and Multilingual LLMs (MLLMs) to enhance MT capabilities in such scenario...

Decoder-only LLMs have shown impressive performance in MT due to their ability to learn from extensive datasets and generate high-quality translations. However, LLMs often struggle with the nuances and style required for organisation-specific translation. In this study, we explore the effectiveness of fine-tuning Large Language Models (LLMs), parti...

This chapter provides a comprehensive overview of the research conducted in the dynamic field of Sign Language Machine Translation (SLMT) over the years. We dissect the SLMT process into a three-component pipeline comprising: (i) sign language recognition, which involves extracting information from input videos containing signed utterances and proc...

Due to the lack of ideal resources, few researchers have investigated how to improve the machine translation (MT) of conversational materials by exploiting their internal structure. In this chapter, we will propose a novel strategy to automatically construct a parallel dialogue corpus by bridging two kinds of resources: movie subtitles and movie sc...

Translating literary works has perennially stood as an elusive dream in machine translation (MT), a journey steeped in intricate challenges. To foster progress in this domain, we hold a new shared task at WMT 2023, the first edition of the Discourse-Level Literary Translation. First, we (Tencent AI Lab and China Literature Ltd.) release a copyright...

When parallel corpora are preprocessed for machine translation (MT) training, a part of the parallel data is commonly discarded and deemed non-parallel due to odd-length ratio, overlapping text in source and target sentences or failing some other form of a semantic equivalency test. For language pairs with limited parallel resources, this can be co...

adaptNMT streamlines all processes involved in the development and deployment of RNN and Transformer neural translation models. As an open-source application, it is designed for both technical and non-technical users who work in the field of machine translation. Built upon the widely-adopted OpenNMT ecosystem, the application is particularly useful...

Within the ELE project three complementary online surveys were designed and implemented to consult the Language Technology (LT) community with regard to the current state of play and the future situation in about 2030 in terms of Digital Language Equality (DLE). While Chapters 4 and 38 provide a general overview of the community consultation method...

This chapter presents the ELE Programme (ELE Consortium 2022). Reacting to the landmark resolution (European Parliament 2018), its vision is to achieve digital language equality in Europe by 2030. The programme was prepared jointly with many stakeholders from the European Language Technology, Natural Language Processing, Computational Linguistics a...

This chapter on existing strategic plans and projects in Language Technology and Artificial Intelligence is based on an analysis of around 200 documents and is divided into three sections. The first provides a synopsis of international and European reports on Language Technology. The second constitutes a review of existing European Strategic Resear...

This chapter provides an introduction to the EU-funded project European Language Equality (ELE). It motivates the project by taking a general look at multilingualism, especially with regard to the political equality of all languages in Europe. Since 2010, several projects and initiatives have developed the notion of utilising sophisticated language...

Machine Translation (MT) is one of the oldest language technologies having been researched for more than 70 years. However, it is only during the last decade that it has been widely accepted by the general public, to the point where in many cases it has become an indispensable tool for the global community, supporting communication between nations...

This chapter presents the concept of Digital Language Equality (DLE) that was at the heart of the European Language Equality (ELE) initiative, and describes the DLE Metric, which includes technological factors (TFs) and contextual factors (CFs): the former concern the availability of Language Resources and Technologies (LRTs) for the languages of E...

We explore different approaches for filtering parallel data for MT training, whether the same filtering approaches suit different datasets, and if separate filters should be applied to a dataset depending on the translation direction. We evaluate the results of different approaches, both manually and on a downstream NMT task. We find that, first, i...

This work presents the development of the translation component in a multistage, multilevel, multimode, multilingual and dynamic deliberative (M4D2) system, built to facilitate automated moderation and translation in the languages of five European countries: Italy, Ireland, Germany, France and Poland. Two main topics were to be addressed in the del...

Due to the ever-changing nature of the human language and the variations in writing style, age-old texts in one language may be incomprehensible to a modern reader. In order to make these texts familiar to the modern reader, we need to rewrite them manually. But this is not always feasible if the volume of texts is very large. In this paper, we pre...

Data selection has proven its merit for improving Neural Machine Translation (NMT), when applied to authentic data. But the benefit of using synthetic data in NMT training, produced by the popular back-translation technique, raises the question if data selection could also be useful for synthetic data? In this work we use Infrequent n-gram Recovery...

Terminology translation plays a crucial role in domain-specific machine translation (MT). Preservation of domain knowledge from source to target is arguably the most concerning factor for clients in translation industry, especially for critical domains such as medical, transportation, military, legal and aerospace. Evaluation of terminology transla...

Consistency is a key requirement of high-quality translation. It is especially important to adhere to pre-approved terminology and corrected translations in domain-specific projects. Machine translation (MT) has achieved significant progress in the area of domain adaptation. However, real-time adaptation remains challenging. Large-scale language mo...

This paper discusses the methods that we used for our submissions to the WMT 2023 Terminology Shared Task for German-to-English (DE-EN), English-to-Czech (EN-CS), and Chinese-to-English (ZH-EN) language pairs. The task aims to advance machine translation (MT) by challenging participants to develop systems that accurately translate technical terms,...

We present SentAlign, an accurate sentence alignment tool designed to handle very large parallel document pairs. Given user-defined parameters, the alignment algorithm evaluates all possible alignment paths in fairly large documents of thousands of sentences and uses a divide-and-conquer approach to align documents containing tens of thousands of s...

Research on Machine Translation (MT) has achieved important breakthroughs in several areas. While there is much more to be done in order to build on this success, we believe that the language industry needs better ways to take full advantage of current achievements. Due to a combination of factors, including time, resources, and skills, businesses...

Preservation of domain knowledge from the source to target is crucial in any translation workflow. It is common in the translation industry to receive highly specialized projects, where there is hardly any parallel in-domain data. In such scenarios where there is insufficient in-domain data to fine-tune Machine Translation (MT) models, producing tr...

Bilingual lexicons can be generated automatically using a wide variety of approaches. We perform a rigorous manual evaluation of four different methods: word alignments on different types of bilingual data, pivoting, machine translation and cross-lingual word embeddings. We investigate how the different setups perform using publicly available data...

Current state-of-the-art neural machine translation (NMT) architectures usually do not take document-level context into account. However, the document-level context of a source sentence to be translated could encode valuable information to guide the MT model to generate a better translation. In recent times, MT researchers have turned their focus t...

Most Indian languages lack sufficient parallel data for Machine Translation (MT) training. In this study, we build English-to-Indian language Neural Machine Translation (NMT) systems using the state-of-the-art transformer architecture. In addition, we investigate the utility of back-translation and its effect on system performance. Our experimental...

Neural machine translation (NMT) systems have greatly improved the quality available from machine translation (MT) compared to statistical machine translation (SMT) systems. However, these state-of-the-art NMT models need much more computing power and data than SMT models, a requirement that is unsustainable in the long run and of very limited bene...

In recent years, neural network-based machine translation (MT) approaches have steadily superseded the statistical MT (SMT) methods, and represents the current state-of-the-art in MT research. Neural MT (NMT) is a data-driven end-to-end learning protocol whose training routine usually requires a large amount of parallel data in order to build a rea...

Neural machine translation (NMT) has emerged as a preferred alternative to the previous mainstream statistical machine translation (SMT) approaches largely due to its ability to produce better translations. The NMT training is often characterized as data hungry since a lot of training data, in the order of a few million parallel sentences, is gener...

This paper describes our contribution to the TIAD 2021 shared task for Translation Inference Across Dictionaries. Our system, PivotAlign, approaches the problem from two directions. First, we collect translation candidates by pivoting through intermediary dictionaries , made available by the task organizers. Second, we decide which candidates to ke...

The Transformer model is the state-of-the-art in Machine Translation. However, in general, neural translation models often under perform on language pairs with insufficient training data. As a consequence, relatively few experiments have been carried out using this architecture on low-resource language pairs. In this study, hyperparameter optimizat...

Translation models for the specific domain of translating Covid data from English to Irish were developed for the LoResMT 2021 shared task. Domain adaptation techniques, using a Covid-adapted generic 55k corpus from the Directorate General of Translation, were applied. Fine-tuning, mixed fine-tuning and combined dataset approaches were compared wit...

The preservation of domain knowledge from source to the target is crucial in any translation workflows. Hence, translation service providers that use machine translation (MT) in production could reasonably expect that the translation process should transfer both the underlying pragmatics and the semantics of the source-side sentences into the targe...

This article presents a review of the evolution of automatic post-editing, a term that describes methods to improve the output of machine translation systems, based on knowledge extracted from datasets that include post-edited content. The article describes the specificity of automatic post-editing in comparison with other tasks in machine translat...

Neural machine translation (NMT) is an approach to machine translation (MT) that uses deep learning techniques, a broad area of machine learning based on deep artificial neural networks (NNs). The book Neural Machine Translation by Philipp Koehn targets a broad range of readers including researchers, scientists, academics, advanced undergraduate or...

Being able to generate accurate word alignments is useful for a variety of tasks. While statistical word aligners can work well, especially when parallel training data are plentiful, multilingual embedding models have recently been shown to give good results in unsupervised scenarios. We evaluate an ensemble method for word alignment on four langua...

Phrase-based statistical machine translation (PB-SMT) has been the dominant paradigm in machine translation (MT) research for more than two decades. Deep neural MT models have been producing state-of-the-art performance across many translation tasks for four to five years. To put it another way, neural MT (NMT) took the place of PB-SMT a few years...

We present graph-based translation models which translate source graphs into target strings. Source graphs are constructed from dependency trees with extra links so that non-syntactic phrases are connected. Inspired by phrase-based models, we first introduce a translation model which segments a graph into a sequence of disjoint subgraphs and genera...

Statistical machine translation (SMT) which was the dominant paradigm in machine translation (MT) research for nearly three decades has recently been superseded by the end-to-end deep learning approaches to MT. Although deep neural models produce state-of-the-art results in many translation tasks, they are found to under-perform on resource-poor sc...

Building Machine Translation (MT) systems for low-resource languages remains challenging. For many language pairs, parallel data are not widely available, and in such cases MT models do not achieve results comparable to those seen with high-resource languages. When data are scarce, it is of paramount importance to make optimal use of the limited ma...

Building a robust MT system requires a sufficiently large parallel corpus to be available as training data. In this paper, we propose to automatically extract parallel sentences from comparable corpora without using any MT system or even any parallel corpus at all. Instead, we use crosslingual information retrieval (CLIR), average word embeddings,...

In machine-learning applications, data selection is of crucial importance if good runtime performance is to be achieved. In a scenario where the test set is accessible when the model is being built, training instances can be selected so they are the most relevant for the test set. Feature Decay Algorithms (FDA) are a technique for data selection th...

In a translation workflow, machine translation (MT) is almost always followed by a human post-editing step, where the raw MT output is corrected to meet required quality standards. To reduce the number of errors human translators need to correct, automatic post-editing (APE) methods have been developed and deployed in such workflows. With the advan...

Sentiment classification has been crucial for many natural language processing (NLP) applications, such as the analysis of movie reviews, tweets, or customer feedback. A sufficiently large amount of data is required to build a robust sentiment classification system. However, such resources are not always available for all domains or for all languag...

Terminology translation plays a critical role in domain-specific machine translation (MT). Phrase-based statistical MT (PB-SMT) has been the dominant approach to MT for the past 30 years, both in academia and industry. Neural MT (NMT), an end-to-end learning approach to MT, is steadily taking the place of PB-SMT. In this paper, we conduct comparati...

The Bidirectional Encoder Representations from Transformers (BERT) model produces state-of-the-art results in many question answering (QA) datasets, including the Stanford Question Answering Dataset (SQuAD). This paper presents a query expansion (QE) method that identifies good terms from input questions, extracts synonyms for the good terms using...

Neural machine translation (NMT) has recently shown promising results on publicly available benchmark datasets and is being rapidly adopted in various production systems. However, it requires high-quality large-scale parallel corpus, and it is not always possible to have sufficiently large corpus as it requires time, money, and professionals. Hence...

Every day, more people are becoming infected and dying from exposure to COVID-19. Some countries in Europe like Spain, France, the UK and Italy have suffered particularly badly from the virus. Others such as Germany appear to have coped extremely well. Both health professionals and the general public are keen to receive up-to-date information on th...

With official status in both Ireland and the EU, there is a need for high-quality English-Irish (EN-GA) machine translation (MT) systems which are suitable for use in a professional translation environment. While we have seen recent research on improving both statistical MT and neural MT for the EN-GA pair, the results of such systems have always b...

Machine translation (MT) has benefited from using synthetic training data originating from translating monolingual corpora, a technique known as backtranslation. Combining backtranslated data from different sources has led to better results than when using such data in isolation. In this work we analyse the impact that data translated with rule-bas...

Every day, more people are becoming infected and dying from exposure to COVID-19. Some countries in Europe like Spain, France, the UK and Italy have suffered particularly badly from the virus. Others such as Germany appear to have coped extremely well. Both health professionals and the general public are keen to receive up-to-date information on th...

Optical character recognition (OCR) for historical documents is a complex procedure subject to a unique set of material issues, including inconsistencies in typefaces and low quality scanning. Consequently, even the most sophisticated OCR engines produce errors. This paper reports on a tool built for postediting the output of Tesseract, more specif...

Thai is a low-resource language, so it is often the case that data is not available in sufficient quantities to train an Neural Machine Translation (NMT) model which perform to a high level of quality. In addition, the Thai script does not use white spaces to delimit the boundaries between words, which adds more complexity when building sequence to...

Despite increasing efforts to improve evaluation of machine translation (MT) by going beyond the sentence level to the document level, the definition of what exactly constitutes a "document level" is still not clear. This work deals with the context span necessary for a more reliable MT evaluation. We report results from a series of surveys involvi...