[DicComb]Commercial_Data_Sheet_UPM_EN(Innovatech)
Web software application for the creation, management and support of combinatorial dictionaries from sets of documents chosen and managed by the user
Writing reports of all kinds, court rulings, a translation, a diagnosis or medical report in a clear and unambiguous way, a language teacher choosing examples and best texts , a lexicographer building a dictionary and looking for representative examples, a journalist looking his best style… have on the bottom the same need. DicComb provides the ability to review material processed from existing documents to enable these people to choose the best way to write something between several proposals. DicComb stands for Combinatorial Dictionary, as this application is based on this kind of dictionary in which the user can manage and process own documents as often as the user likes and then build a customized dictionary and style guide.
The product is available as a web application for using by subscription or installed in intranets, which includes the ability to upload amounts of documents in different formats (pdf, doc, docx and txt at least) to be processed (debugging, counting terminological term extraction, stemming) at rates exceeding 1.000 words/sec. The result will select either the combinations of words as the representative examples that a user would choose to build a corporate or thematic dictionary that supports copy-editing.
- why is it different: there is not a similar application in Spanish language (also in Portuguese and Russian, which are being analyzed to penetrate the market of these languages ).
- why is it innovative: these tools, which do not exist at the moment, allow the standardization of production methods texts in any field.
“Let’s combine the words accurately, rigorously and easily”
- Processing of written texts properly, accurately and in less time, aimed to the following groups:
- Judges and Lawyers (judgments, orders)
- Medical / clinical (diagnostic reports)
- Researchers (description of the language)
- Language teachers (preparation of teaching materials)
- Translators (finding the best expression)
- Lexicographers (construction of dictionaries)
- Editorials (definition of a style)
- Journalists (normalization style)
- Content providers
- Writers
- Some figures on the potential would be (pending better evaluation):
- Lawyers: more than 1,600 law firms over 3 lawyers in Spain.
- Teachers of Spanish (first language and as a foreign language): more than 18 million students of Spanish in the world.
- Health care facility
- Translators
- lexicographers
- Journalists
- Editorials
- Market analysis done to exploit the solution in Brazil.
- Reduce time and costs dictionary definition process.
- Increased accuracy and productivity in the drafting of reports and similar ones.
- Developing intuitive and user interfaces for users with less experience in combinatorial lexicography and dictionaries.
- Improvements in knowledge management processes in companies and institutions.
- Low implementation costs as web application.
- Suported by UPM Validation and Business Applications Group: moren than 20 years experience in this field and international contacts.
- DAIL spin-off creation for the market development (3rd prize in actúaupm competition 2011).
- Group elected in 1996 to represent the Spanish Language in the multilingual Internet project of the United Nations.
- Key group of UNESCO Chair in language technologies (in process of final acceptance).
- Concept
- R&D
- Lab-Prototype
- Industrial Prototype
- Production
DicComb contact
Jesús Cardeñosa
e: carde@fi.upm.es
Carolina Gallardo
e: cgallardo@eui.upm.es
w: http://www.vai.dia.fi.upm.es
UPM contact
Innovation, Commercialization and Entrepreneurship Area
Centre of Support for Technological Innovation – UPM
e: innovacion.tecnologica@upm.es