Antonio Valerio Miceli Barone

Antonio Valerio Miceli Barone
The University of Edinburgh | UoE · School of Informatics

Computer Engineering

About

31
Publications
14,018
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
1,039
Citations
Additional affiliations
January 2010 - July 2015
Università di Pisa
Position
  • PhD Student

Publications

Publications (31)
Article
We present a survey covering the state of the art in low-resource machine translation research. There are currently around 7000 languages spoken in the world and almost all language pairs lack significant resources for training machine translation models. There has been increasing interest in research addressing the challenge of producing useful tr...
Preprint
Full-text available
Neural machine learning models can successfully model language that is similar to their training distribution, but they are highly susceptible to degradation under distribution shift, which occurs in many practical applications when processing out-of-domain (OOD) text. This has been attributed to "shortcut learning": relying on weak correlations ov...
Preprint
Full-text available
We present a survey covering the state of the art in low-resource machine translation. There are currently around 7000 languages spoken in the world and almost all language pairs lack significant resources for training machine translation models. There has been increasing interest in research addressing the challenge of producing useful translation...
Conference Paper
Full-text available
This paper describes the joint submission to the IWSLT 2019 English to Czech task by Samsung R&D Institute, Poland, and the University of Edinburgh. Our submission was ultimately produced by combining four Transformer systems through a mixture of ensembling and reranking.
Preprint
The University of Edinburgh participated in the WMT19 Shared Task on News Translation in six language directions: English-to-Gujarati, Gujarati-to-English, English-to-Chinese, Chinese-to-English, German-to-English, and English-to-Czech. For all translation directions, we created or used back-translations of monolingual data in the target language a...
Conference Paper
Full-text available
The limited availability of in-domain training data is a major issue in the training of application-specific neural machine translation models. Professional outsourcing of bilingual data collections is costly and often not feasible. In this paper we analyze the influence of using crowdsourcing as a scalable way to obtain translations of target in-d...
Conference Paper
Full-text available
This paper reports on a comparative evaluation of phrase-based statistical machine translation (PBSMT) and neural machine translation (NMT) for four language pairs, using the PET interface to compare educational domain output from both systems using a variety of metrics, including automatic evaluation as well as human rankings of adequacy and fluen...
Article
Full-text available
This paper describes the University of Edinburgh's submissions to the WMT17 shared news translation and biomedical translation tasks. We participated in 12 translation directions for news, translating between English and Czech, German, Latvian, Russian, Turkish and Chinese. For the biomedical task we submitted systems for English to Czech, German,...
Article
Full-text available
We investigate techniques for supervised domain adaptation for neural machine translation where an existing model trained on a large out-of-domain dataset is adapted to a small in-domain dataset. In this scenario, overfitting is a major challenge. We investigate a number of techniques to reduce overfitting and improve transfer learning, including r...
Article
Full-text available
It has been shown that increasing model depth improves the quality of neural machine translation. However, different architectural variants to increase model depth have been proposed, and so far, there has been no thorough comparative study. In this work, we describe and evaluate several existing approaches to introduce depth in neural machine tran...
Article
Full-text available
Automated documentation of programming source code and automated code generation from natural language are challenging tasks of both practical and scientific interest. Progress in these areas has been limited by the low availability of parallel corpora of code and natural language descriptions, which tend to be small and constrained to specific dom...
Conference Paper
Full-text available
We present Nematus, a toolkit for Neural Machine Translation. The toolkit prioritizes high translation accuracy, usability, and extensibility. Nematus has been used to build top-performing submissions to shared translation tasks at WMT and IWSLT, and has been used to train systems for production environments.
Article
Full-text available
We present Nematus, a toolkit for Neural Machine Translation. The toolkit prioritizes high translation accuracy, usability, and extensibility. Nematus has been used to build top-performing submissions to shared translation tasks at WMT and IWSLT, and has been used to train systems for production environments.
Conference Paper
Full-text available
Current approaches to learning vector representations of text that are compatible between different languages usually require some amount of parallel text, aligned at word, sentence or at least document level. We hypothesize however, that different natural languages share enough semantic structure that it should be possible, in principle, to learn...
Article
Current approaches to learning vector representations of text that are compatible between different languages usually require some amount of parallel text, aligned at word, sentence or at least document level. We hypothesize however, that different natural languages share enough semantic structure that it should be possible, in principle, to learn...
Article
Full-text available
Deep learning consists in training neural networks to perform computations that sequentially unfold in many steps over a time dimension or an intrinsic depth dimension. Effective learning in this setting is usually accomplished by specialized network architectures that are designed to mitigate the vanishing gradient problem of naive deep networks....
Conference Paper
Full-text available
The quality of statistical machine translation performed with phrase based approaches can be increased by permuting the words in the source sentences in an order which resembles that of the target language. We propose a class of recurrent neural models which exploit source-side dependency syntax features to reorder the words into a target-like orde...
Conference Paper
Full-text available
We describe a N-best reranking model based on features that combine source-side dependency syntactical information and segmentation and alignment information. Specifically, we consider segmentation-aware " phrase dependency " features.
Article
Full-text available
The quality of statistical machine translation performed with phrase based approaches can be increased by permuting the words in the source sentences in an order which resembles that of the target language. We propose a class of recurrent neural models which exploit source-side dependency syntax features to reorder the words into a target-like orde...
Conference Paper
Full-text available
Dependency Parsing domain adaptation involves adapting a dependency parser, trained on an annotated corpus from a given domain (e.g., newspaper articles), to work on a different target domain (e.g., legal documents), given only an unannotated corpus from the target domain. We present a shift/reduce dependency parser that can handle unlabeled senten...
Conference Paper
We present a translation model based on dependency trees. The model adopts a tree-to-string approach and extends Phrase-Based translation (PBT) by using the dependency tree of the source sentence for selecting translation options and for reordering them. Decoding is done by translating each node in the tree and combining its translations with those...

Projects

Project (1)
Project
TraMOOC (Translation for Massive Open Online Courses) is a Horizon 2020 collaborative project aiming at providing reliable machine Translation for Massive Open Online Courses (MOOCs). The main result of the project will be an online translation platform, which will utilize a wide set of linguistic infrastructure tools and resources in order to provide accurate and coherent translation to its end users.