no code implementations • JEPTALNRECITAL 2012 • Haithem Afli, Lo{\"\i}c Barrault, Holger Schwenk
no code implementations • LREC 2016 • Haithem Afli, Zhengwei Qiu, Andy Way, P{\'a}raic Sheridan
A trend to digitize historical paper-based archives has emerged in recent years, with the advent of digital optical scanners.
no code implementations • WS 2016 • Haithem Afli, Andy Way
Such documents must be passed through a process of Optical Character Recognition (OCR) to render the text suitable for MT.
no code implementations • WS 2017 • Ahmad Khwileh, Haithem Afli, Gareth Jones, Andy Way
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.
no code implementations • WS 2017 • Haithem Afli, Pintu Lohar, Andy Way
Integrating Natural Language Processing (NLP) and computer vision is a promising effort.
Content-Based Image Retrieval Multimodal Machine Translation
no code implementations • IJCNLP 2017 • Pintu Lohar, Koel Dutta Chowdhury, Haithem Afli, Mohammed Hasanuzzaman, Andy Way
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.
no code implementations • SEMEVAL 2019 • Abdessalam Bouchekif, Praveen Joshi, Latifa Bouchekif, Haithem Afli
Our proposed system is based on the combination of different deep neural networks techniques.
no code implementations • WS 2019 • Gael de Francony, Victor Guichard, Praveen Joshi, Haithem Afli, Abdessalam Bouchekif
In this paper, we present two approaches for Arabic Fine-Grained Dialect Identification.
no code implementations • 19 Sep 2021 • Praveen Joshi, Chandra Thapa, Seyit Camtepe, Mohammed Hasanuzzamana, Ted Scully, Haithem Afli
Federated Learning (FL), Split Learning (SL), and SplitFed Learning (SFL) are three recent developments in distributed machine learning that are gaining attention due to their ability to preserve the privacy of raw data.
no code implementations • 7 Apr 2022 • Praveen Joshi, Mohammed Hasanuzzaman, Chandra Thapa, Haithem Afli, Ted Scully
Secondly, this paper presents enabling technologies, such as model parallelism and split learning, which facilitate DL training and deployment at edge servers.
no code implementations • 25 Jul 2023 • Praveen Joshi, Chandra Thapa, Mohammed Hasanuzzaman, Ted Scully, Haithem Afli
Among various techniques in a DCML framework, federated split learning, known as splitfed learning (SFL), is the most suitable for efficient training and testing when devices have limited computational capabilities.
no code implementations • MTSummit 2021 • Séamus Lankford, Haithem Afli, Andy Way
Translation models for the specific domain of translating Covid data from English to Irish were developed for the LoResMT 2021 shared task.
no code implementations • 4 Mar 2024 • Séamus Lankford, Haithem Afli, Andy Way
adaptNMT streamlines all processes involved in the development and deployment of RNN and Transformer neural translation models.
no code implementations • 4 Mar 2024 • Séamus Lankford, Haithem Afli, Andy Way
Our findings show the best-performing Transformer system significantly reduces both accuracy and fluency errors when compared with an RNN-based model.
1 code implementation • 4 Mar 2024 • Séamus Lankford, Haithem Afli, Andy Way
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).
no code implementations • 4 Mar 2024 • Séamus Lankford, Haithem Afli, Andy Way
The Transformer model is the state-of-the-art in Machine Translation.
1 code implementation • 6 Mar 2024 • Séamus Lankford, Haithem Afli, Órla Ní Loinsigh, Andy Way
However in the context of low-resource languages, there is a paucity of parallel data datasets available for developing translation models.
no code implementations • 6 Mar 2024 • Séamus Lankford, Haithem Afli, Andy Way
adaptNMT is an open-source application that offers a streamlined approach to the development and deployment of Recurrent Neural Networks and Transformer models.
1 code implementation • LREC 2022 • Séamus Lankford, Haithem Afli, Órla Ní Loinsigh, Andy Way
However in the context of low-resource languages, there is a paucity of parallel data datasets available for developing translation models.
no code implementations • PoliticalNLP (LREC) 2022 • Desline Simon, Sheila Castilho, Pintu Lohar, Haithem Afli
Sarcasm is extensively used in User Generated Content (UGC) in order to express one’s discontent, especially through blogs, forums, or social media such as Twitter.