Search Results for author:
Found 141 papers, 17 papers with code
The ADAPT Centre’s Participation in WAT 2020 English-to-Odia Translation Task
This paper describes the ADAPT Centre sub-missions to WAT 2020 for the English-to-Odia translation task.
Terminology-Aware Sentence Mining for NMT Domain Adaptation: ADAPT’s Submission to the Adap-MT 2020 English-to-Hindi AI Translation Shared Task
This paper describes the ADAPT Centre’s submission to the Adap-MT 2020 AI Translation Shared Task for English-to-Hindi.
DELA Corpus - A Document-Level Corpus Annotated with Context-Related Issues
Recently, the Machine Translation (MT) community has become more interested in document-level evaluation especially in light of reactions to claims of “human parity”, since examining the quality at the level of the document rather than at the sentence level allows for the assessment of suprasentential context, providing a more reliable evaluation.
Neural Machine Translation for translating into Croatian and Serbian
Furthermore, translation performance from English is much better than from German, partly because German is morphologically more complex and partly because the corpus consists mostly of parallel human translations instead of original text and its human translation.
An Error-based Investigation of Statistical and Neural Machine Translation Performance on Hindi-to-Tamil and English-to-Tamil
Statistical machine translation (SMT) was the state-of-the-art in machine translation (MT) research for more than two decades, but has since been superseded by neural MT (NMT).
The ADAPT Centre’s Neural MT Systems for the WAT 2020 Document-Level Translation Task
In this paper we describe the ADAPT Centre’s submissions to the WAT 2020 document-level Business Scene Dialogue (BSD) Translation task.
Knowledge Distillation for Sustainable Neural Machine Translation
Knowledge distillation (KD) can be used to reduce model size and training time, without significant loss in performance.
CombAlign: a Tool for Obtaining High-Quality Word Alignments
Being able to generate accurate word alignments is useful for a variety of tasks.
The ADAPT’s Submissions to the WMT20 Biomedical Translation Task
This paper describes the ADAPT Centre’s submissions to the WMT20 Biomedical Translation Shared Task for English-to-Basque.
The ADAPT System Description for the WMT20 News Translation Task
This paper describes the ADAPT Centre’s submissions to the WMT20 News translation shared task for English-to-Tamil and Tamil-to-English.
MTrill project: Machine Translation impact on language learning
The literature on MT and Computer Assisted Language Learning (CALL) shows that, over the years, MT systems have been facilitating language teaching and also language learning (Nin ̃o, 2006).
Progress of the PRINCIPLE Project: Promoting MT for Croatian, Icelandic, Irish and Norwegian
This paper updates the progress made on the PRINCIPLE project, a 2-year action funded by the European Commission under the Connecting Europe Facility (CEF) programme.
A human evaluation of English-Irish statistical and neural machine translation
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.
MT syntactic priming effects on L2 English speakers
In this paper, we tested 20 Brazilian Portuguese speakers at intermediate and advanced English proficiency levels to investigate the influence of Google Translate’s MT system on the mental processing of English as a second language.
Modelling Source- and Target- Language Syntactic Information as Conditional Context in Interactive Neural Machine Translation
In this study, we model source-language syntactic constituency parse and target-language syntactic descriptions in the form of supertags as conditional context for interactive prediction in neural MT (NMT).
Introducing the Digital Language Equality Metric: Technological Factors
The paper situates this ongoing work with a strong European focus in the broader context of related efforts, and explains how the DLE Metric can help track the progress towards DLE for all languages of Europe, focusing in particular on the role played by the TFs.
Developing Machine Translation Engines for Multilingual Participatory Spaces
It is often a challenging task to build Machine Translation (MT) engines for a specific domain due to the lack of parallel data in that area.
Overview of the ELE Project
This paper provides an overview of the ongoing European Language Equality(ELE) project, an 18-month action funded by the European Commission which involves 52 partners.
Achievements of the PRINCIPLE Project: Promoting MT for Croatian, Icelandic, Irish and Norwegian
This paper provides an overview of the main achievements of the completed PRINCIPLE project, a 2-year action funded by the European Commission under the Connecting Europe Facility (CEF) programme.
Effective Bitext Extraction From Comparable Corpora Using a Combination of Three Different Approaches
Parallel sentences extracted from comparable corpora can be useful to supplement parallel corpora when training machine translation (MT) systems.
On Machine Translation of User Reviews
This work investigates neural machine translation (NMT) systems for translating English user reviews into Croatian and Serbian, two similar morphologically complex languages.
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.
Transformers for Low-Resource Languages: Is Féidir Linn!
The Transformer model is the state-of-the-art in Machine Translation.
Investigating Low-resource Machine Translation for English-to-Tamil
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.
gaHealth: An English–Irish Bilingual Corpus of Health Data
However in the context of low-resource languages, there is a paucity of parallel data datasets available for developing translation models.
Compiling a Highly Accurate Bilingual Lexicon by Combining Different Approaches
By combining the most promising approaches and data sets, using confidence scores calculated from the data and the results of manually evaluating samples from our manual evaluation as indicators, we are able to induce lists of translations with a very high acceptance rate.
Identifying Complaints from Product Reviews: A Case Study on Hindi
Automatic recognition of customer complaints on products or services that they purchase can be crucial for the organisations, multinationals and online retailers since they can exploit this information to fulfil their customers’ expectations including managing and resolving the complaints.
gaHealth: An English-Irish Bilingual Corpus of Health Data
However in the context of low-resource languages, there is a paucity of parallel data datasets available for developing translation models.
Design of an Open-Source Architecture for Neural Machine Translation
adaptNMT is an open-source application that offers a streamlined approach to the development and deployment of Recurrent Neural Networks and Transformer models.
adaptNMT: an open-source, language-agnostic development environment for Neural Machine Translation
adaptNMT streamlines all processes involved in the development and deployment of RNN and Transformer neural translation models.
Human Evaluation of English--Irish Transformer-Based NMT
Our findings show the best-performing Transformer system significantly reduces both accuracy and fluency errors when compared with an RNN-based model.
Transformers for Low-Resource Languages:Is Féidir Linn!
The Transformer model is the state-of-the-art in Machine Translation.
adaptMLLM: Fine-Tuning Multilingual Language Models on Low-Resource Languages with Integrated LLM Playgrounds
As a multilingual tool, we used adaptMLLM to fine-tune models for two low-resource language pairs: English to Irish (EN$\leftrightarrow$GA) and English to Marathi (EN$\leftrightarrow$MR).
Machine Translation in the Covid domain: an English-Irish case study for LoResMT 2021
Translation models for the specific domain of translating Covid data from English to Irish were developed for the LoResMT 2021 shared task.
Fine-tuning Large Language Models for Adaptive Machine Translation
These findings emphasise the significance of fine-tuning efficient LLMs like Mistral 7B to yield high-quality zero-shot translations comparable to task-oriented models like NLLB 3. 3B.
SentAlign: Accurate and Scalable Sentence Alignment
We present SentAlign, an accurate sentence alignment tool designed to handle very large parallel document pairs.
Findings of the WMT 2023 Shared Task on Discourse-Level Literary Translation: A Fresh Orb in the Cosmos of LLMs
To foster progress in this domain, we hold a new shared task at WMT 2023, the first edition of the Discourse-Level Literary Translation.
Adaptive Machine Translation with Large Language Models
By feeding an LLM at inference time with a prompt that consists of a list of translation pairs, it can then simulate the domain and style characteristics.
Translation Word-Level Auto-Completion: What can we achieve out of the box?
Research on Machine Translation (MT) has achieved important breakthroughs in several areas.
Domain-Specific Text Generation for Machine Translation
Preservation of domain knowledge from the source to target is crucial in any translation workflow.
Dependency Graph-to-String Statistical Machine Translation
We present graph-based translation models which translate source graphs into target strings.
Arabisc: Context-Sensitive Neural Spelling Checker
Accordingly, we made use of a bidirectional LSTM language model (LM) for our context-sensitive spelling detection and correction model which is shown to have much control over the correction process.
Using Multiple Subwords to Improve English-Esperanto Automated Literary Translation Quality
As an additional contribution, we made available a set of English-Esperanto parallel data in the literary domain.
The Impact of Indirect Machine Translation on Sentiment Classification
Furthermore, as performing a direct translation is not always possible, we explore the performance of automatic classifiers on sentences that have been translated using a pivot MT system.
The ADAPT System Description for the STAPLE 2020 English-to-Portuguese Translation Task
This paper describes the ADAPT Centre{'}s submission to STAPLE (Simultaneous Translation and Paraphrase for Language Education) 2020, a shared task of the 4th Workshop on Neural Generation and Translation (WNGT), for the English-to-Portuguese translation task.
Effectively Aligning and Filtering Parallel Corpora under Sparse Data Conditions
When rich morphology exacerbates the data sparsity problem, it is imperative to have accurate alignment and filtering methods that can help make the most of what is available by maximising the number of correctly translated segments in a corpus and minimising noise by removing incorrect translations and segments containing extraneous data.
On Context Span Needed for Machine Translation Evaluation
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.
ELRI: A Decentralised Network of National Relay Stations to Collect, Prepare and Share Language Resources
We describe the European Language Resource Infrastructure (ELRI), a decentralised network to help collect, prepare and share language resources.
Selecting Backtranslated Data from Multiple Sources for Improved Neural Machine Translation
Machine translation (MT) has benefited from using synthetic training data originating from translating monolingual corpora, a technique known as backtranslation.
Facilitating Access to Multilingual COVID-19 Information via Neural Machine Translation
Every day, more people are becoming infected and dying from exposure to COVID-19.
Multiple Segmentations of Thai Sentences for Neural Machine Translation
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.
A Tool for Facilitating OCR Postediting in Historical Documents
This paper reports on a tool built for postediting the output of Tesseract, more specifically for correcting common errors in digitized historical documents.
The European Language Technology Landscape in 2020: Language-Centric and Human-Centric AI for Cross-Cultural Communication in Multilingual Europe
Multilingualism is a cultural cornerstone of Europe and firmly anchored in the European treaties including full language equality.
Selecting Artificially-Generated Sentences for Fine-Tuning Neural Machine Translation
Neural Machine Translation (NMT) models tend to achieve best performance when larger sets of parallel sentences are provided for training.
Getting Gender Right in Neural Machine Translation
Our contribution is two-fold: (1) the compilation of large datasets with speaker information for 20 language pairs, and (2) a simple set of experiments that incorporate gender information into NMT for multiple language pairs.
Combining SMT and NMT Back-Translated Data for Efficient NMT
Neural Machine Translation (NMT) models achieve their best performance when large sets of parallel data are used for training.
Investigating Terminology Translation in Statistical and Neural Machine Translation: A Case Study on English-to-Hindi and Hindi-to-English
Terminology translation plays a critical role in domain-specific machine translation (MT).
Combining PBSMT and NMT Back-translated Data for Efficient NMT
Neural Machine Translation (NMT) models achieve their best performance when large sets of parallel data are used for training.
Transductive Data-Selection Algorithms for Fine-Tuning Neural Machine Translation
Machine Translation models are trained to translate a variety of documents from one language into another.
Building English-to-Serbian Machine Translation System for IMDb Movie Reviews
This paper reports the results of the first experiment dealing with the challenges of building a machine translation system for user-generated content involving a complex South Slavic language.
Lost in Translation: Loss and Decay of Linguistic Richness in Machine Translation
This work presents an empirical approach to quantifying the loss of lexical richness in Machine Translation (MT) systems compared to Human Translation (HT).
Adaptation of Machine Translation Models with Back-translated Data using Transductive Data Selection Methods
These methods ensure that selected sentences share n-grams with the test set so the NMT model can be adapted to translate it.
No Padding Please: Efficient Neural Handwriting Recognition
Neural handwriting recognition (NHR) is the recognition of handwritten text with deep learning models, such as multi-dimensional long short-term memory (MDLSTM) recurrent neural networks.
Ranked #15 on
Handwritten Text Recognition
on IAM
ABI Neural Ensemble Model for Gender Prediction Adapt Bar-Ilan Submission for the CLIN29 Shared Task on Gender Prediction
In contradiction with the results described in previous comparable shared tasks, our neural models performed better than our best traditional approaches with our best feature set-up.
The ADAPT System Description for the IWSLT 2018 Basque to English Translation Task
In this paper we present the ADAPT system built for the Basque to English Low Resource MT Evaluation Campaign.
Data Selection with Feature Decay Algorithms Using an Approximated Target Side
A limitation of these methods to date is that using the source-side test set does not by itself guarantee that sentences are selected with correct translations, or translations that are suitable given the test-set domain.
Learning to Jointly Translate and Predict Dropped Pronouns with a Shared Reconstruction Mechanism
Pronouns are frequently omitted in pro-drop languages, such as Chinese, generally leading to significant challenges with respect to the production of complete translations.
Extracting In-domain Training Corpora for Neural Machine Translation Using Data Selection Methods
Data selection is a process used in selecting a subset of parallel data for the training of machine translation (MT) systems, so that 1) resources for training might be reduced, 2) trained models could perform better than those trained with the whole corpus, and/or 3) trained models are more tailored to specific domains.
Multi-Level Structured Self-Attentions for Distantly Supervised Relation Extraction
Targeting the MIL issue, the structured sentence-level attention learns a 2-D matrix where each row vector represents a weight distribution on selection of different valid in-stances.
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.
Incorporating Deep Visual Features into Multiobjective based Multi-view Search Results Clustering
Current paper explores the use of multi-view learning for search result clustering.
Tailoring Neural Architectures for Translating from Morphologically Rich Languages
A morphologically complex word (MCW) is a hierarchical constituent with meaning-preserving subunits, so word-based models which rely on surface forms might not be powerful enough to translate such structures.
SuperNMT: Neural Machine Translation with Semantic Supersenses and Syntactic Supertags
In this paper we incorporate semantic supersensetags and syntactic supertag features into EN{--}FR and EN{--}DE factored NMT systems.
Fine-Grained Temporal Orientation and its Relationship with Psycho-Demographic Correlates
In this paper, we propose a very first study to demonstrate the association between the sentiment view of the temporal orientation of the users and their different psycho-demographic attributes by analyzing their tweets.
Investigating Backtranslation in Neural Machine Translation
A prerequisite for training corpus-based machine translation (MT) systems -- either Statistical MT (SMT) or Neural MT (NMT) -- is the availability of high-quality parallel data.
Improving Character-based Decoding Using Target-Side Morphological Information for Neural Machine Translation
Recently, neural machine translation (NMT) has emerged as a powerful alternative to conventional statistical approaches.
Quality expectations of machine translation
Machine Translation (MT) is being deployed for a range of use-cases by millions of people on a daily basis.
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.
ADAPT at IJCNLP-2017 Task 4: A Multinomial Naive Bayes Classification Approach for Customer Feedback Analysis task
In this paper, we analyse the real world samples of customer feedback from Microsoft Office customers in four languages, i. e., English, French, Spanish and Japanese and conclude a five-plus-one-classes categorisation (comment, request, bug, complaint, meaningless and undetermined) for meaning classification.
Semantics-Enhanced Task-Oriented Dialogue Translation: A Case Study on Hotel Booking
We showcase TODAY, a semantics-enhanced task-oriented dialogue translation system, whose novelties are: (i) task-oriented named entity (NE) definition and a hybrid strategy for NE recognition and translation; and (ii) a novel grounded semantic method for dialogue understanding and task-order management.
Demographic Word Embeddings for Racism Detection on Twitter
Most social media platforms grant users freedom of speech by allowing them to freely express their thoughts, beliefs, and opinions.
MultiNews: A Web collection of an Aligned Multimodal and Multilingual Corpus
Integrating Natural Language Processing (NLP) and computer vision is a promising effort.
Content-Based Image Retrieval
Multimodal Machine Translation
Exploiting Cross-Sentence Context for Neural Machine Translation
In translation, considering the document as a whole can help to resolve ambiguities and inconsistencies.
Context-Aware Graph Segmentation for Graph-Based Translation
In this paper, we present an improved graph-based translation model which segments an input graph into node-induced subgraphs by taking source context into consideration.
Using Images to Improve Machine-Translating E-Commerce Product Listings.
We evaluate our models quantitatively using BLEU and TER and find that (i) additional synthetic data has a general positive impact on text-only and multi-modal NMT models, and that (ii) using a multi-modal NMT model for re-ranking n-best lists improves TER significantly across different n-best list sizes.
Human Evaluation of Multi-modal Neural Machine Translation: A Case-Study on E-Commerce Listing Titles
Nonetheless, human evaluators ranked translations from a multi-modal NMT model as better than those of a text-only NMT over 88{\%} of the time, which suggests that images do help NMT in this use-case.
Ethical Considerations in NLP Shared Tasks
Shared tasks are increasingly common in our field, and new challenges are suggested at almost every conference and workshop.
Identifying Effective Translations for Cross-lingual Arabic-to-English User-generated Speech Search
Cross Language Information Retrieval (CLIR) systems are a valuable tool to enable speakers of one language to search for content of interest expressed in a different language.
Fast Gated Neural Domain Adaptation: Language Model as a Case Study
We show that the neural LM perplexity can be reduced by 7. 395 and 12. 011 using the proposed domain adaptation mechanism on the Penn Treebank and News data, respectively.
Enriching Phrase Tables for Statistical Machine Translation Using Mixed Embeddings
PBSMT engines by default provide four probability scores in phrase tables which are considered as the main set of bilingual features.
Topic-Informed Neural Machine Translation
In recent years, neural machine translation (NMT) has demonstrated state-of-the-art machine translation (MT) performance.
Integrating Optical Character Recognition and Machine Translation of Historical Documents
Such documents must be passed through a process of Optical Character Recognition (OCR) to render the text suitable for MT.
Automatic Construction of Discourse Corpora for Dialogue Translation
Then tags such as speaker and discourse boundary from the script data are projected to its subtitle data via an information retrieval approach in order to map monolingual discourse to bilingual texts.
Using SMT for OCR Error Correction of Historical Texts
A trend to digitize historical paper-based archives has emerged in recent years, with the advent of digital optical scanners.
Enhancing Access to Online Education: Quality Machine Translation of MOOC Content
The present work is an overview of the TraMOOC (Translation for Massive Open Online Courses) research and innovation project, a machine translation approach for online educational content.
ProphetMT: A Tree-based SMT-driven Controlled Language Authoring/Post-Editing Tool
This paper presents ProphetMT, a tree-based SMT-driven Controlled Language (CL) authoring and post-editing tool.
Using BabelNet to Improve OOV Coverage in SMT
Out-of-vocabulary words (OOVs) are a ubiquitous and difficult problem in statistical machine translation (SMT).
A Novel Approach to Dropped Pronoun Translation
Finally, we integrate the above outputs into our translation system to recall missing pronouns by both extracting rules from the DP-labelled training data and translating the DP-generated input sentences.
SUMAT: Data Collection and Parallel Corpus Compilation for Machine Translation of Subtitles
Subtitling and audiovisual translation have been recognized as areas that could greatly benefit from the introduction of Statistical Machine Translation (SMT) followed by post-editing, in order to increase efficiency of subtitle production process.
