The Research Group in Computational Linguistics at the University of Wolverhampton is currently recruiting a Reader in Translation Technology (permanent) and a Research Fellow in Translation Technology (3 year position with the possibility of extension). The purpose of these posts is to strengthen the research group by enhancing its research and publications in the field of translation technology. The appointed candidates will be expected to produce REF-returnable outputs, attract external income, seek industrial collaborations, teach at Masters level and supervise PhD students. Continue reading
The successfully completed FIRST project has developed various components which help users to analyse the complexity of texts and rewrite texts in order to make them more accessible for readers with Autistic Spectrum Disorder (ASD). These components were integrated in the OpenBook tool, but they cannot be used in isolation. In an attempt to make some of this technology available for other researchers, we started a process of releasing some of the components individually. The first component to be released as a web demo is the syntactic
complexity sign tagger. This is a tool that assigns words and punctuation marks from a predefined set to categories indicating their syntactic linking and bounding functions. Some of these categories are used by our sentence rewriting algorithm. Continue reading
Richard Evans, University of Wolverhampton
Date and time: Wednesday, June 22nd, 11:30
Evidence from clinical linguistics and NLP shows that sentences which are propositionally dense and syntactically complex are relatively difficult to process by humans and machines. Continue reading
Elena Errico, University of Genoa
Title: An Interpreter’s Wish List
Date and time: Tuesday 7th June, 1.30pm
Room: MC232, City Campus
Interpreting is a very challenging cognitive activity not least because it requires professionals to take translation decisions under very strict time constraints and while performing several Continue reading
The programme and the abstracts of the presentations of the 2nd Workshop on Natural Language Processing for Translation Memories to be held in conjunction with LREC 2016 is available on the workshops website. It features three invited speakers, four research papers, a shared task and a round table. We hope to see you in Portorož.
Speaker: Shiva Taslimipoor
Title: Automatic Extraction and Translation of Multiword Expressions
Date and time: Wednesday, March 9th, 2pm
Room: MD083, City Campus
Abstract: Multiword expressions (MWEs) are defined as idiosyncratic interpretations that cross word boundaries or spaces, e.g. frying pan, take a look and take part. They have distinct syntactic and semantic properties that call for special treatment within a computational system. Continue reading
Speaker: Dr Paul Rayson, Lancaster University
Title: Taxonomies for semantic tagging: how large do they need to be?
Date and time: Tuesday Feb 9th, 2pm
Room: MI301, City Campus
Abstract: In this presentation, I will describe joint research carried out in the recently completed Samuels project (www.gla.ac.uk/samuels/) in which we have applied automatic semantic analysis to two very large corpora around 1-2 billion words each: Continue reading
The details of the shared task on cleaning of translation memories organised at the 2nd Workshop on Natural Language Processing for Translation Memories have been published. We hope it will be a successful task given the amount of traffic the page has received in the first 24h since it was announced.
The second call for papers for the 2nd Workshop on Natural Language Processing for Translation Memories (NLP4TM 2016) to be organised in conjunction with LREC 2016 has been distributed. The deadline for paper submission is in 2 week. For more details please visit the workshop’s web page.
- Constantin Orasan (University of Wolverhampton, UK)
- Marcello Federico (FBK, Italy)
Submission deadline: May 15, 2016
1. Call For Papers
Translation Memories (TM) are amongst the most widely used tools by professional translators. The underlying idea of TMs is that a translator should benefit as much as possible from previous translations by being able to retrieve the way in which a similar sentence was translated before. Moreover, the usage of TMs aims to guarantee that new translations follow the client’s specified style and terminology. Despite the fact that the core idea of these systems relies on comparing segments (typically of sentence length) from the document to be translated with segments from previous translations, most of the existing TM systems hardly use any language processing for this. Instead of addressing this issue, most of the work on translation memories focused on improving the user experience by allowing processing of a variety of document formats, intuitive user interfaces, etc. Continue reading