Details of Grant 

EPSRC Reference:	GR/T04540/01
Title:	Statistical Models for Text-to-text Generation
Principal Investigator:	Lapata, Professor M
Other Investigators:
Researcher Co-Investigators:
Project Partners:
Department:	Sch of Informatics
Organisation:	University of Edinburgh
Scheme:	Advanced Fellowship (Pre-FEC)
Starts:	01 February 2005	Ends:	28 February 2011	Value (£):	289,541
EPSRC Research Topic Classifications:	Comput./Corpus Linguistics Information & Knowledge Mgmt
EPSRC Industrial Sector Classifications:	Creative Industries
Related Grants:
Panel History:	Panel Date Panel Name Outcome 19 Apr 2004 ICT Fellowships 2004 - ARF Interview Panel Deferred 18 Mar 2004 ICT Fellowships 2004 Sift Panel Deferred
Summary on Grant Application Form
An emerging area of research in the field of Natural Language Processing (NLP) is text-to-text generation. Text-to-text generation takes naturally occurring texts as input and transforms them into new texts satisfying constraints such as length or style. Examples of applications that require text-to-text generation are single- and multidocument summarization, text simplification, sentence compression, and question answering. At the heart of methods developed for text-to-text generation lies the ability to identify and generate paraphrases, i.e., alternative ways to convey the same information either at the sentence or at the document level.The aim of this fellowship is to investigate text-rewriting and develop corpus-based models that capture alternative ways to convey the same information. We will adopt a data intensive approach where meaning equivalences will be learned directly from text samples by exploiting what is observable in the data rather than manually specified rules, or elaborate semantic representations. Such an approach can deal with different text genres and domains, it is robust (i.e., it has the potential to yield paraphrases required for front end applications without the scalability bottleneck associated with handcrafted methods), and relatively inexpensive as it assumes that crucial semantic information can be discovered by analysing the linguistic environment as approximated by large corpora.
Key Findings
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
Potential use in non-academic contexts
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
Impacts
Description This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk Summary Date Materialised
Sectors submitted by the Researcher
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
Project URL:
Further Information:
Organisation Website:	http://www.ed.ac.uk