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. Before starting this role, I was Reader 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 have received my BSc in computer science at Babeș-Bolyai University, Cluj-Napoca, Romania and was awarded my PhD from the University of Wolverhampton.
I have over 20 years experience of working in the fields of (applied) Natural Language Processing (NLP), Artificial Intelligence and Machine Learning for language processing. My research interests are largely focused on facilitating information access and include translation technology, sentiment analysis, question answering, text summarisation, anaphora and coreference resolution, building, annotation and exploitation of corpora.
I recently coordinated the EXPERT project, an extremely successful Initial Training Network (ITN) funded under the People Programme of the Seventh Framework Programme (FP7) of the European Community which trained the next generation of world-class researchers in the field of data-driven translation technology. In addition to coordinating this project between nine partners across both academia and industry, I was actively involved in the training of the Early Stage Researchers (ESRs) appointed in the project and, in collaboration with these ESRs, I carried out research on translation memories and quality estimation for machine translation. I continue researching these topics.
I was also the deputy coordinator of the FIRST project, a project which developed language technologies for making texts more accessible to people with autism. In addition to managing a consortium of nine partners from academia, industry and heath care organisations, I also carried out research on text simplification and contributed to the development of a powerful editor which can be used by carers of people with autism to make texts more accessible for these people.
In the past In the past, I was the Local Course Coordinator of the Erasmus Mundus programme on Technology for Translation and Interpretation and the Erasmus Mundus International Masters in Natural Language Processing and Human Language Technology, and the scientist in charge for the University of Wolverhampton in two European projects QALL-ME and MESSAGE. I also worked as a research fellow on the CAST project.
I love programming and in my spare time I contribute to some open source projects and have my own GitHub repository.
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.