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.
no code implementations • RANLP (BUCC) 2021 • Steinþór Steingrímsson, Pintu Lohar, Hrafn Loftsson, Andy Way
Parallel sentences extracted from comparable corpora can be useful to supplement parallel corpora when training machine translation (MT) systems.
no code implementations • EAMT 2022 • Pintu Lohar, Guodong Xie, Andy Way
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.
no code implementations • AMTA 2022 • Pintu Lohar, Sinead Madden, Edmond O’Connor, Maja Popovic, Tanya Habruseva
Moreover, we developed a first-ever test parallel data set of product descriptions.
no code implementations • AMTA 2020 • Alberto Poncelas, Pintu Lohar, Andy Way, James Hadley
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.
1 code implementation • WS 2019 • Pintu Lohar, Maja Popovi{\'c}, Andy Way
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.
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 • 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 • EACL 2017 • Iacer Calixto, Daniel Stein, Evgeny Matusov, Pintu Lohar, Sheila Castilho, Andy Way
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.