Change search
Link to record
Permanent link

Direct link
BETA
Publications (2 of 2) Show all publications
Berg, J., Domeij, R., Edlund, J., Eriksson, G., Fallgren, P., House, D., . . . Öqvist, J. (2019). Making Archival Speech Recordings Accessible for Research: A Report from the Tilltal Project. Svenska landsmål och svenskt folkliv, 141, 171-178
Open this publication in new window or tab >>Making Archival Speech Recordings Accessible for Research: A Report from the Tilltal Project
Show others...
2019 (English)In: Svenska landsmål och svenskt folkliv, ISSN 0347-1837, Vol. 141, p. 171-178Article in journal (Other academic) Published
Place, publisher, year, edition, pages
Kungl. Skogs- och Lantbruksakademien, 2019
Keywords
Tilltal, talinspelningar
National Category
Humanities and the Arts General Language Studies and Linguistics Specific Languages
Research subject
Language History; Dialectology; Language Technology; Language Technology
Identifiers
urn:nbn:se:sprakochfolkminnen:diva-1677 (URN)
Projects
Tilltal
Funder
Riksbankens Jubileumsfond, SAF16-0917:1
Note

Projektet Tillgängligt kulturarv för forskning i tal (Tilltal) undersöker hur talteknologiska metoder kan göra historiska talinspelningar mer tillgängliga för forskare.

Available from: 2019-08-21 Created: 2019-08-21 Last updated: 2019-09-16Bibliographically approved
Eriksson, G. & Karlgren, J. (2012). Features for modelling characteristics of conversations: Notebook for PAN at CLEF 2012. In: CLEF 2012 Evaluation Labs and Workshop Online Working Notes: . Paper presented at CLEF 2012 Evaluation Labs and Workshop, Rome, Italy, 17-20 September 2012.
Open this publication in new window or tab >>Features for modelling characteristics of conversations: Notebook for PAN at CLEF 2012
2012 (English)In: CLEF 2012 Evaluation Labs and Workshop Online Working Notes, 2012Conference paper, Oral presentation only (Refereed)
Abstract [en]

In this experiment, we find that features which model interaction andconversational behaviour contribute well to identifying sexual grooming behaviourin chat and forum text. Together with the obviously useful lexical features —which we find are more valuable if separated by who generates them — weachieve very successful results in identifying behavioural patterns which maycharacterise sexual grooming. We conjecture that the general framework can beused for other purposes than this specific case if the lexical features are exchangedfor other topical models, the conversational features characterise interaction andbehaviour rather than topical choice.

National Category
Language Technology (Computational Linguistics)
Identifiers
urn:nbn:se:sprakochfolkminnen:diva-1191 (URN)
Conference
CLEF 2012 Evaluation Labs and Workshop, Rome, Italy, 17-20 September 2012
Note

QC 20130204

Available from: 2017-12-15 Created: 2017-12-15 Last updated: 2018-01-13
Organisations
Identifiers
ORCID iD: ORCID iD iconorcid.org/0000-0001-6949-6380

Search in DiVA

Show all publications