Search Results for author:
Found 66 papers, 26 papers with code
Building Domain-specific Corpora from the Web: the Case of European Digital Service Infrastructures
An important goal of the MaCoCu project is to improve EU-specific NLP systems that concern their Digital Service Infrastructures (DSIs).
Low-Resource Unsupervised NMT: Diagnosing the Problem and Providing a Linguistically Motivated Solution
Unsupervised Machine Translation has been advancing our ability to translate without parallel data, but state-of-the-art methods assume an abundance of monolingual data.
Machine Translation for English–Inuktitut with Segmentation, Data Acquisition and Pre-Training
Translating to and from low-resource polysynthetic languages present numerous challenges for NMT.
Dr. Livingstone, I presume? Polishing of foreign character identification in literary texts
Character identification is a key element for many narrative-related tasks.
Automatic Discrimination of Human and Neural Machine Translation: A Study with Multiple Pre-Trained Models and Longer Context
We address the task of automatically distinguishing between human-translated (HT) and machine translated (MT) texts.
CREAMT: Creativity and narrative engagement of literary texts translated by translators and NMT
We present here the EU-funded project CREAMT that seeks to understand what is meant by creativity in different translation modalities, e. g. machine translation, post-editing or professional translation.
MaCoCu: Massive collection and curation of monolingual and bilingual data: focus on under-resourced languages
We introduce the project “MaCoCu: Massive collection and curation of monolingual and bilingual data: focus on under-resourced languages”, funded by the Connecting Europe Facility, which is aimed at building monolingual and parallel corpora for under-resourced European languages.
Man vs. Machine: Extracting Character Networks from Human and Machine Translations
Most of the work on Character Networks to date is limited to monolingual texts.
Using Wordnet to Improve Reordering in Hierarchical Phrase-Based Statistical Machine Translation
We propose the use of WordNet synsets in a syntax-based reordering model for hierarchical statistical machine translation (HPB-SMT) to enable the model to generalize to phrases not seen in the training data but that have equivalent meaning.
Unsupervised Translation of German–Lower Sorbian: Exploring Training and Novel Transfer Methods on a Low-Resource Language
This paper describes the methods behind the systems submitted by the University of Groningen for the WMT 2021 Unsupervised Machine Translation task for German–Lower Sorbian (DE–DSB): a high-resource language to a low-resource one.
Data Selection for Unsupervised Translation of German–Upper Sorbian
This paper describes the methods behind the systems submitted by the University of Groningen for the WMT 2020 Unsupervised Machine Translation task for German–Upper Sorbian.
Do Language Models Care About Text Quality? Evaluating Web-Crawled Corpora Across 11 Languages
Large, curated, web-crawled corpora play a vital role in training language models (LMs).
To be or not to be: a translation reception study of a literary text translated into Dutch and Catalan using machine translation
The results show that HT presented a higher engagement, enjoyment and translation reception in Catalan if compared to PE and MT.
Automatic Discrimination of Human and Neural Machine Translation in Multilingual Scenarios
We tackle the task of automatically discriminating between human and machine translations.
Multilingual Multi-Figurative Language Detection
Figures of speech help people express abstract concepts and evoke stronger emotions than literal expressions, thereby making texts more creative and engaging.
Missing Information, Unresponsive Authors, Experimental Flaws: The Impossibility of Assessing the Reproducibility of Previous Human Evaluations in NLP
We report our efforts in identifying a set of previous human evaluations in NLP that would be suitable for a coordinated study examining what makes human evaluations in NLP more/less reproducible.
Multidimensional Evaluation for Text Style Transfer Using ChatGPT
We investigate the potential of ChatGPT as a multidimensional evaluator for the task of \emph{Text Style Transfer}, alongside, and in comparison to, existing automatic metrics as well as human judgements.
Are Character-level Translations Worth the Wait? Comparing ByT5 and mT5 for Machine Translation
Pretrained character-level and byte-level language models have been shown to be competitive with popular subword models across a range of Natural Language Processing (NLP) tasks.
Subword-Delimited Downsampling for Better Character-Level Translation
This new downsampling method not only outperforms existing downsampling methods, showing that downsampling characters can be done without sacrificing quality, but also leads to promising performance compared to subword models for translation.
Patching Leaks in the Charformer for Efficient Character-Level Generation
Character-based representations have important advantages over subword-based ones for morphologically rich languages.
DivEMT: Neural Machine Translation Post-Editing Effort Across Typologically Diverse Languages
We publicly release the complete dataset including all collected behavioral data, to foster new research on the translation capabilities of NMT systems for typologically diverse languages.
The Importance of Context in Very Low Resource Language Modeling
This paper investigates very low resource language model pretraining, when less than 100 thousand sentences are available.
Human Judgement as a Compass to Navigate Automatic Metrics for Formality Transfer
Although text style transfer has witnessed rapid development in recent years, there is as yet no established standard for evaluation, which is performed using several automatic metrics, lacking the possibility of always resorting to human judgement.
Creativity in translation: machine translation as a constraint for literary texts
This article presents the results of a study involving the translation of a short story by Kurt Vonnegut from English to Catalan and Dutch using three modalities: machine-translation (MT), post-editing (PE) and translation without aid (HT).
Multilingual Pre-training with Language and Task Adaptation for Multilingual Text Style Transfer
We exploit the pre-trained seq2seq model mBART for multilingual text style transfer.
Unsupervised Translation of German--Lower Sorbian: Exploring Training and Novel Transfer Methods on a Low-Resource Language
Lastly, we experiment with the order in which offline and online back-translation are used to train an unsupervised system, finding that using online back-translation first works better for DE$\rightarrow$DSB by 2. 76 BLEU.
Generic resources are what you need: Style transfer tasks without task-specific parallel training data
Style transfer aims to rewrite a source text in a different target style while preserving its content.
Thank you BART! Rewarding Pre-Trained Models Improves Formality Style Transfer
Scarcity of parallel data causes formality style transfer models to have scarce success in preserving content.
The Impact of Post-editing and Machine Translation on Creativity and Reading Experience
The results show that HT presented a higher creativity score if compared to MTPE and MT.
Machine Translation of Novels in the Age of Transformer
In this chapter we build a machine translation (MT) system tailored to the literary domain, specifically to novels, based on the state-of-the-art architecture in neural MT (NMT), the Transformer (Vaswani et al., 2017), for the translation direction English-to-Catalan.
Character-level Representations Improve DRS-based Semantic Parsing Even in the Age of BERT
We combine character-level and contextual language model representations to improve performance on Discourse Representation Structure parsing.
Ranked #1 on
DRS Parsing
on PMB-2.2.0
Fine-grained Human Evaluation of Transformer and Recurrent Approaches to Neural Machine Translation for English-to-Chinese
This research presents a fine-grained human evaluation to compare the Transformer and recurrent approaches to neural machine translation (MT), on the translation direction English-to-Chinese.
Reassessing Claims of Human Parity and Super-Human Performance in Machine Translation at WMT 2019
We reassess the claims of human parity and super-human performance made at the news shared task of WMT 2019 for three translation directions: English-to-German, English-to-Russian and German-to-English.
A Set of Recommendations for Assessing Human-Machine Parity in Language Translation
The quality of machine translation has increased remarkably over the past years, to the degree that it was found to be indistinguishable from professional human translation in a number of empirical investigations.
Neural Machine Translation for English--Kazakh with Morphological Segmentation and Synthetic Data
This paper presents the systems submitted by the University of Groningen to the English{--} Kazakh language pair (both translation directions) for the WMT 2019 news translation task.
Post-editese: an Exacerbated Translationese
We conduct a set of computational analyses in which we compare PE against HT on three different datasets that cover five translation directions with measures that address different translation universals and laws of translation: simplification, normalisation and interference.
The Effect of Translationese in Machine Translation Test Sets
The effect of translationese has been studied in the field of machine translation (MT), mostly with respect to training data.
Linguistic Information in Neural Semantic Parsing with Multiple Encoders
Recently, sequence-to-sequence models have achieved impressive performance on a number of semantic parsing tasks.
Ranked #2 on
DRS Parsing
on PMB-3.0.0
Exploring Neural Methods for Parsing Discourse Representation Structures
Neural methods have had several recent successes in semantic parsing, though they have yet to face the challenge of producing meaning representations based on formal semantics.
Ranked #3 on
DRS Parsing
on PMB-3.0.0
Attaining the Unattainable? Reassessing Claims of Human Parity in Neural Machine Translation
We reassess a recent study (Hassan et al., 2018) that claimed that machine translation (MT) has reached human parity for the translation of news from Chinese into English, using pairwise ranking and considering three variables that were not taken into account in that previous study: the language in which the source side of the test set was originally written, the translation proficiency of the evaluators, and the provision of inter-sentential context.
Quantitative Fine-Grained Human Evaluation of Machine Translation Systems: a Case Study on English to Croatian
This paper presents a quantitative fine-grained manual evaluation approach to comparing the performance of different machine translation (MT) systems.
What Level of Quality can Neural Machine Translation Attain on Literary Text?
Given the rise of a new approach to MT, Neural MT (NMT), and its promising performance on different text types, we assess the translation quality it can attain on what is perceived to be the greatest challenge for MT: literary text.
Fine-grained human evaluation of neural versus phrase-based machine translation
We compare three approaches to statistical machine translation (pure phrase-based, factored phrase-based and neural) by performing a fine-grained manual evaluation via error annotation of the systems' outputs.
A Multifaceted Evaluation of Neural versus Phrase-Based Machine Translation for 9 Language Directions
We aim to shed light on the strengths and weaknesses of the newly introduced neural machine translation paradigm.
Producing Monolingual and Parallel Web Corpora at the Same Time - SpiderLing and Bitextor's Love Affair
This paper presents an approach for building large monolingual corpora and, at the same time, extracting parallel data by crawling the top-level domain of a given language of interest.
TweetMT: A Parallel Microblog Corpus
We introduce TweetMT, a parallel corpus of tweets in four language pairs that combine five languages (Spanish from/to Basque, Catalan, Galician and Portuguese), all of which have an official status in the Iberian Peninsula.
Enhancing Cross-border EU E-commerce through Machine Translation: Needed Language Resources, Challenges and Opportunities
This paper discusses the role that statistical machine translation (SMT) can play in the development of cross-border EU e-commerce, by highlighting extant obstacles and identifying relevant technologies to overcome them.
TLAXCALA: a multilingual corpus of independent news
We acquire corpora from the domain of independent news from the Tlaxcala website.
caWaC -- A web corpus of Catalan and its application to language modeling and machine translation
In this paper we present the construction process of a web corpus of Catalan built from the content of the . cat top-level domain.
Quality Estimation for Synthetic Parallel Data Generation
This paper presents a novel approach for parallel data generation using machine translation and quality estimation.
Towards a User-Friendly Platform for Building Language Resources based on Web Services
This paper presents the platform developed in the PANACEA project, a distributed factory that automates the stages involved in the acquisition, production, updating and maintenance of Language Resources required by Machine Translation and other Language Technologies.
