TranSent: Translation of sentiment in text
Start date
2020End date
2023About the project
Summary
TranSent is a broad project funded part of the E3 expansion which investigates challenges that have to be addressed when translating texts which contain sentiments and emotions, and aims to develop methods that improve the translation of such texts. To achieve this, the project aims to combine expertise from a number of areas such as Natural Language Process, Linguistics, Translation Studies and Psycholinguistics.
The current focus of the project is on understanding how off the shelf translation engines, such as Google Translate, perform when they translate user generated content (e.g. product reviews posted on sites like Amazon, Booking.com, or tweets). This research direction is motivated by the fact an increasing number of companies use translation engines to offer their visitors access to content that is not written in a language they can understand. The research carried out so far focused on book reviews written in Arabic and proposed a method for tuning an Neural Machine Translation (NMT) engine to improve the translation of contronyms from Arabic into English. We are currently working on several other language pairs and focusing on more linguistic phenomena.
Outcomes
The project has carried out an error analysis of translation errors introduced by Google translate when it is used to translate book reviews from Arabic to English. The results of this error analysis are presented in (Sadaany and Orasan, 2020). This data was also used to tune a Neural Machine Translation engine to produce better translations of sentences containing contronyms and to explore ways to automatically assess the quality of translation of sentences which contain sentiments.
Publications
Hadeel Saadany, Constantin Orăsan (2020) Is it Great or Terrible? Preserving Sentiment in Neural Machine Translation of Arabic Reviews, Proceedings of the Fifth Arabic Natural Language Processing Workshop, p. 24-37.
Presentations
- 28 Nov 2020: Translation of Sentiment in Multilingual User Generated Content at the 56th Linguistics Colloquium
- 12 Dec 2020: Is it Great or Terrible? Preserving Sentiment in Neural Machine Translation of Arabic Reviews, presentation at the Fifth Arabic Natural Language Processing Workshop
People
Principle Investigator
Professor Constantin Orasan
Professor of Language and Translation Technologies
Biography
I am Professor of Language and Translation Technologies at the Centre of Translation Studies, University of Surrey, UK, and a Fellow of the Surrey Institute for People-Centred Artificial Intelligence. Before starting this role, I was Reader (Associate Professor) in Computational Linguistics at the University of Wolverhampton, UK, and the deputy head of the Research Group in Computational Linguistics at the same university. I hold a PhD in computational linguistics and a BSc in computer science.
With over 25 years of experience in the fields of Natural Language Processing, Artificial Intelligence, and Linguistics, I have established myself as a leading researcher in the development of technologies that facilitate access to information. My PhD was in automatic summarisation, and I have led projects on question answering, text simplification, and translation technologies. Notable projects that I have led are EmpASR, an AHRC-funded project focused on training interpreters on how to benefit from the latest developments in artificial intelligence; HarnessingNLP4Court, a UKRI-funded project focused on facilitating access to legal information; the EXPERT project, an Initial Training Network (ITN) funded under the EU’s FP7 to train the next generation of world-class researchers in the field of data-driven translation technology; and the FIRST project, which developed language technologies for making texts more accessible to people with autism.
My current research is interdisciplinary, focusing on the intersection of AI, NLP, and translation studies. In recent years, I have increasingly focused on the practical application of NLP to support translators and interpreters. My recent publications explore reference-less translation evaluation, the processing of multilingual content in low-resource settings, the use of automatic speech recognition to support interpreters, and the use of large language models in text accessibility. My research is well known as a result of over 150 peer-reviewed articles in journals, books, and international conferences.
I am currently leading an EPSRC-funded project focused on making science accessible, and I am Co-Director of the ADA Leverhulme Doctoral Scholarships Network. More information about my work can be found at https://dinel.org.uk/.
Contact
For enquiries or potential collaboration on this topic please contact Professor Constantin Orasan, the Principal Investigator of the project.
See other research projects carried out at the Centre for Translation Studies.