"False"
Skip to content
printicon
Main menu hidden.

Image: AdobeStock: Tierney

Foundations of Language Processing

Research group Languages, formal or natural, permeate our intellectual and practical lives. When agents, computer or human, wish to communicate something, they must encode it in some type of language. We study how languages can be processed based on their structure, and how their semantics or meaning can be extracted.

Languages are typically defined by syntactic rules or well-formedness constraints, and their sentences are commonly associated with some type of semantics or meaning. Moreover, language is usually embedded in the context of other information-bearing content. Perhaps the most obvious example is video, where language appears in the form of text (subtitles) and speech, but there is also visual content and there may be metadata embedded in the video.

The research group Foundations of Language Processing studies the theoretical and practical aspects of representing language on computers, and its interconnection with other sources of information. The work of the group spans from the theoretical analysis of formal languages as a theoretical basis for XML and linguistic applications to the study, practical implementation, and application of multimodal media analysis.

Head of research

Suna Bensch
Associate professor
E-mail
Email
Henrik Björklund
Associate professor
E-mail
Email
Johanna Björklund
Associate professor
E-mail
Email
Adam Dahlgren Lindström
Postdoctoral fellow
E-mail
Email
Anton Eklund
Doctoral student
E-mail
Email
Emil Häglund
Doctoral student
E-mail
Email
Anna Jonsson
Associate professor
E-mail
Email
Lena Strobl
Doctoral student
E-mail
Email
Somayeh Jafaritazehjani
Research engineer
E-mail
Email
Martin Berglund
Associate professor
E-mail
Email
Willeke Martens
Doctoral student
E-mail
Email

Overview

Participating departments and units at Umeå University

Department of Computing Science

Research area

Computing science

Research projects

SAVANT – Self-optimising Video Platform for Affiliate Marketing
Research area: Computing science
Duration 1 March 2018 until 29 February 2020
Type of project Research project
Syntactical methods for text classification
Duration 1 November 2014 until 30 September 2017
Type of project Research project
MICO - Media in context
Duration 1 May 2013 until 30 April 2016
Type of project Research project
Parameterized Natural Language Parsing
Duration 12 October 2012 until 6 February 2020
Type of project Research project

Latest publications

Journal of Current Issues and Research in Advertising
Häglund, Emil; Björklund, Johanna
AI & Society: The Journal of Human-Centred Systems and Machine Intelligence, Springer 2024, Vol. 39 : 811-813
Hellström, Thomas; Bensch, Suna
Proceedings of the 6th International Conference on Natural Language and Speech Processing (ICNLSP 2023), Association for Computational Linguistics 2023 : 68-77
Hatefi, Arezoo; Vu, Xuan-Son; Bhuyan, Monowar H.; et al.
Northern European Journal of Language Technology (NEJLT), Linköping University Electronic Press 2023, Vol. 9, (1)
Eklund, Anton; Forsman, Mona; Drewes, Frank
Proceedings of the third workshop on language technology for equality, diversity, inclusion, The Association for Computational Linguistics 2023 : 54-61
Björklund, Henrik; Devinney, Hannah
Graph Transformation: 15th International Conference, ICGT 2022, Held as Part of STAF 2022, Nantes, France, July 7–8, 2022, Proceedings, Cham: Springer 2022 : 3-19
Drewes, Frank; Hoffmann, Berthold; Minas, Mark
Acta Informatica, Springer Nature 2021, Vol. 58 : 177-194
Björklund, Johanna; Cleophas, Loek
Man som läser nyheter på en läsplatta.
Deep-learning models provides relevant ads without tracking users

New thesis shows how AI can be used to categorise news articles and improve contextual advertising.

Awarded 4 million SEK for developing new Deep Learning methods

Johanna Björklund receives funding for research on semantic parsing of multimodal data.

Latest update: 2021-09-06