Hoppa till huvudinnehåll

Alla nyheter

Projektet MAÞiR tilldelas anslag från Wallenbergfond

Det treåriga projektet MAÞiR: Methods for the automatic Analysis of Text in digital Historical Resources har tilldelats 3,4 miljoner kronor från Markus och Amalia Wallenbergs minnesfond. Projektledare är FD Gerlof Bouma och målet med projektet är att utforska språkvetenskaplig databehandling för fornsvenska (ca 1225-1526). Genom projektet kommer också historiska texter med lingvistisk uppmärkning att tillgängliggöras för språkvetare och forskare från andra discipliner med interesse för detta kulturarv.

Språkbanken åker till Nodalida

Den 22 till 24 maj åker en stor del av Språkbankens personal till konferensen Nodalida (http://www.hf.uio.no/nodalida/) som i år hålls i Oslo. Förutom att vi är med och arrangerar fyra av fyra workshopar, är vi delaktiga i fyra workshop-bidrag samt fyra bidrag till huvudkonferensen. Vi ser fram emot många givande möten och diskussioner!

News about Korp

In there stepped a stately Raven of the saintly days of yore.
the silence was unbroken, and the stillness gave no token,

Until now! 'Tis surely been a long time since last we corresponded, due compensation to follow.

A major new feature sets its foot on the Night's Plutonian shore – introducing the new Trend Diagram feature with which you can:

  • visualize language change over time from the statistics tab
  • display data as line or bars
  • click on data points to to see the hits in the kwic view
  • make crazy advanced stuff happen by fiddling with 'compile based on...' (sammanställ på) before searching.

 

And the rare and radiant maiden whom the angels name Malin has dumped, wikileaks style, a pile of diplomatic correspondence to the lab's Old Swedish mode. You should check that out.

Martin, sitting lonely on the placid bust, has hardly been slacking off either. Besides bringing the backend magic to the trend diagram he's also added a whole host of password protected corpora and people have been getting access to those left and right, smiles all around. You'll also have noticed the twitter mix and smiled some more.

And the Raven, never flitting, still is sitting, still is sitting

We'll happily accept bug reports, let us know of any issues.

By these angels he hath sent thee,
The Korponauts

Projektet Mining textual data for simplified reading tilldelas anslag från Wallenbergfond

Projektet Mining textual data for simplified reading har tilldelats 5 miljoner kronor från Markus och Amalia Wallenbergs minnesfond. Projektet är treårigt och leds av professor Arne Jönsson vid Linköpings universitet, med projektdeltagare vid Språkbanken.

 

Projektsammanfattning på engelska:

If students can find texts that are adapted to their reading abilities, the information becomes more accessible, and easier for them to transform to knowledge. Students with reading problems get easier texts whereas students with no reading problems get more advanced texts. Individually adapted simplifications of the texts will further support the students' learning, and stimulate their interest in reading, increase their actual reading efforts and facilitate source critique, as they understand the texts better.

In the project we will develop sophisticated measures for assessing a student’s reading ability and a tool for the student and teacher to create a profile of this ability. We will also investigate how these measures can be transformed to values on known criteria like vocabulary, grammatical fluency and so forth, and how these can be used to analyse texts. Such text criteria, sensitive to content, readability and genre in combination with the profile of a student’s reading ability will form the base to individually adapted texts. Techniques and tools will be developed for selecting suitable texts, automatic summarisation of texts to a length that is adapted to the individual student and for automatic transformation to easy-to-read Swedish.