| 1. |
- Domeij, Rickard, et al.
(författare)
-
Workshop on NLP for Reading and Writing : Resources, algorithms and tools
- 2008
-
Ingår i: Swedish Conference of Language Technology, 2008. - 1736-6305. ; VOL. 3
-
Konferensbidrag (refereegranskat)abstract
- New tools and media are creating new possibilities for people to communicate and find information over the Internet in a multilingual, global society. This is reflected in the fact that writers now write more in everyday life, typically create text directly on the computer and on the Internet (e.g. on blogs and other Web 2.0 technologies), and use new forms of writing in e-mails, web chats or SMS-messages on mobile phones. This concerns not only adults at work, but also children and youth. However, the new possibilities also put higher demands on our skills in using language for achieving our communicative goals in different situations. If the demands are not met, a great number of people will risk being excluded from participation in the emerging information society. Of course, this will have unfortunate consequences not only for the individual, but also for society at large. Therefore, there is a growing need for support in reading and writing. Certainly, there already exists writing tools such as authoring aids in word processors and instructional support in writing education. However, existing solutions have great difficulties meeting the growing need of support. In part, this is due to technical limitations of the tools in processing language, but also to the fact that these tools are poorly adjusted to different tasks, target user groups, genres and media.
|
|
| 2. |
|
|
| 3. |
|
|
| 4. |
|
|
| 5. |
|
|
| 6. |
|
|
| 7. |
- Kokkinakis, Dimitrios, 1965, et al.
(författare)
-
Literacy Demands and Information to Cancer Patients
- 2012
-
Ingår i: Proceedings of the 15th International Conference on Text, Speech and Dialogue. - Berlin, Heidelberg : Springer Berlin Heidelberg. - 0302-9743. - 9783642327896
-
Konferensbidrag (refereegranskat)abstract
- This study examines language complexity of written health information materials for patients undergoing colorectal cancer surgery. Written and printed patient information from 28 Swedish clinics are automatically analyzed by means of language technology. The analysis reveals different problematic issues that might have impact on readability. The study is a first step, and part of a larger project about patients’ health information seeking behavior in relation to written information material. Our study aims to provide support for producing more individualized, person centered information materials according to preferences for complex and detailed or legible texts and thus enhance a movement from receiving information and instructions to participating in knowing. In the near future the study will continue by integrating focus groups with patients that may provide valuable feedback and enhance our knowledge about patients’ use and preferences of different information material.
|
|
| 8. |
|
|
| 9. |
- Volodina, Elena, 1973, et al.
(författare)
-
Semi-automatic selection of best corpus examples for Swedish: Initial algorithm evaluation.
- 2012
-
Ingår i: Proceedings of the SLTC 2012 workshop on NLP for CALL, Lund, 25th October, 2012.. - 1650-3740. ; :080, s. 59-70
-
Konferensbidrag (refereegranskat)abstract
- The study presented here describes the results of the initial evaluation of two sorting approaches to automatic ranking of corpus examples for Swedish. Representatives from two potential target user groups have been asked to rate top three hits per approach for sixty search items from the point of view of the needs of their professional target groups, namely second/foreign language (L2) teachers and lexicographers. This evaluation has shown, on the one hand, which of the two approaches to example rating (called in the text below algorithms #1 and #2) performs better in terms of finding better examples for each target user group; and on the other hand, which features evaluators associate with good examples. It has also facilitated statistic analysis of the “good” versus “bad” examples with reference to the measurable features, such as sentence length, word length, lexical frequency profiles, PoS constitution, dependency structure, etc. with a potential to find out new reliable classifiers.
|
|
| 10. |
- Carlund, Carina, et al.
(författare)
-
An academic word list for Swedish - a support for language learners in higher education
- 2012
-
Ingår i: Proceedings of the SLTC 2012 workshop on NLP for CALL, Lund, 25th October, 2012. - : Linköping University Electronic Press. - 1650-3740. ; , s. 20-27
-
Tidskriftsartikel (refereegranskat)abstract
- The paper describes the ongoing development of compiling and introducing a Swedish academic word list (SAWL), inter alia intended to be used as a lexical resource in CALL-applications in relation to higher academic studies. When it comes to language acquisition, resources like these play an important part in instructed language learning. So far, no such resource exists for Swedish. The format of SAWL has been elaborated in collaboration with the Language Support Service at the University of Gothenburg. SAWL is compiled with methods from corpus linguistics inspired by research on English academic words (Coxhead 2002). Our work includes collection and syntactic annotation of learner corpora of Swedish academic texts from a wide range of university subjects within the Faculty of Arts. The corpora are freely accessible through Språkbanken. SAWL are designed with university students and language learners with Swedish or other linguistic backgrounds in mind. The word list and the corpora can be used for studies of one’s own or in classroom situations, as well as forming a component of computer computerbased language assessment and CALLrelated application platforms.
|
|
