Supervisory appointments
Currently supervising
- Jonathan Piller at SU (with professors Sindri Magnusson and Jaakko Hollmén and Mariano Beguerisse at Spotify) 2021-
- Filip Cornell at KTH (with professor Šarūnas Girdzijauskas) 2019-
Graduated Doctoral and Licentiate candidates
- 2017: Stanley Greenstein
Our Humanity Exposed: Predictive Modelling in a Legal Context in Law and Informatics at Stockholm University (with professor Peter Wahlgren)
- 2014: Ann-Marie Eklund
The Game of Health Search, Gothenburg University (with professors Dimitrios Kokkinakis and Lars Borin)
- 2013: Oscar Täckström
Predicting Linguistic Structure with Incomplete and Cross-Lingual Supervision, Uppsala University, Linguistics (with professor Joakim Nivre)
- 2011: Atelach Alemu Argaw
Resource Lenient Approaches to Cross Language Information Retrieval using Amharic, Stockholm University, Computer and Systems Sciences. (co-advisor with professor Lars Asker)
- 2010: Karin Friberg Heppin
Resolving Power of Search Keys in MedEval a Swedish Medical Test Collection with User Groups: Doctors and Patients, Language Technology, Gothenburg University. (with professor Lars Borin)
- 2009: Rikard Lindell
"Jag älskar att allt ligger överst": En designstudie av ytinteraktion för kollaborativa multimedia-framträdanden, Computer Technology, Mälardalen University College. (with professors Morten Fjeld and Jonas Löwgren)
- 2006: Magnus Sahlgren
Word Space Models, Stockholm University, Computational Linguistics.
- 2006: Leif Grönqvist
Exploring Latent Semantic Vector Models Enriched With N-grams. Datavetenskap, Växjö University. (with professor Joakim Nivre)
- 2004: Rikard Lindell
Towards new Interaction - A Content Centric Data Surface Approach. Computer Technology, Mälardalen University College. (Licentiate dissertation)
- 2001: Anette Hulth
The Gist of Written Documents: Automatic Derivation and Evaluation of Content Descriptors, Stockholm University, Computer and Systems Sciences. (co-advisor with professor Lars Asker)
Graduated Bachelor and Master candidates
- Julius Leino. 2024. Controlling the Text Generation of a Large Language Model in Multilingual Setting using Latent Space Steering
Diplomiyö, tuotantotalous. Aalto-yliopisto.
- John Magnusson. 2021. Finding time-based listening habits in users music listening history to lower entropy in data Magisteruppsats i datalogi. KTH
- Winstead Zhu. 2021. Hotspot Detection for Automatic Podcast Trailer Generation. Magisteruppsats i språkteknologi. Uppsala universitet. (med Joakim Nivre och Md Iftekhar Tanveer.).
- Beichen Chen. 2021. Stylometric Embeddings for Book Similarities Magisteruppsats i datalogi. KTH.
- Stavros Giorgis 2021. Evaluation of Approaches for Representation and Sentiment of Customer Reviews. 2021. MSc Thesis in Computer Science and Engineering. KTH.
- Pratima Rao Akinepally 2020. Investigating Performance of Different Models at Short Text Topic Modelling. MSc Thesis in Computer Science and Engineering. KTH. (With Maria Movin.)
- Nils Balzar Ekenbäck. 2020. Evaluation of Sentence Representations in Semantic Text Similarity Tasks . Magisteruppsats i datalogi. KTH.
- Marcus Lindström. 2020. The Impact of Scaling Down a Language Model Used for Text Summarization. Magisteruppsats i datalogi. KTH.
- Katariina Martikainen. 2020. Audio-based stylistic characteristics of Podcasts for search and recommendation : a user and computational analysis. M Sc thesis in interaction studies, University of Twente and KTH.
- Suhas Shehadri. 2019. Identifying Action related Dialogue Acts in Meetings: Research into identifying Action Items, Decisions, and Ideas from multi-party meeting transcripts. Magisteruppsats i datalogi. KTH.
- Rithika Harish Kumar. 2019. Spelling Correction To Improve Classification Of Technical Error Reports. Magisteruppsats i datalogi. KTH.
- Gustav Gränsbo. 2019. Word Clustering in an Interactive Text Analysis Tool. Magisteruppsats i datavetenskap. Linköpings universitet.
- Elena Fano. 2019. A comparative study of word embedding methods for early risk prediction on the Internet. Magisteruppsats i språkteknologi. Uppsala universitet. (med Joakim Nivre).
- Vasileios Kalogiras. 2017. Sentiment Classification with Deep Neural Networks. Magisteruppsats i datalogi. KTH. (With Magnus Sahlgren).
- Hugo Sandelius. 2016. Creating Knowledge Graphs using Distributional Semantic Models..Magisteruppsats i datalogi. KTH. (med Magnus Sahlgren)
- Kerry Zhang. 2016. Viewpoint and Topic Modeling of Current Events. Kandidatuppsats i datalogi. (med Cheng Zhang) KTH.
- Vide Karlsson. 2016. Nyckelordsbaserade textkategoriseringsalgoritmer - en lösning på problemet att automatiskt ämneskategorisera text utan tillgång till handetiketterad träningsdata?. Examensarbete i datalogi. (med Pawel Herman) KTH.
- Kajsa Norin. 2016. Higher Order Hidden Markov Models for Dialogue Act Tagging and Detection of Disputes in Online Forums. Master's thesis in Computer Science. Uppsala. (with Michael Ashcroft)
- Christopher Norman. 2015. Technical Term Extraction Using Measures of Neology Master's thesis in Computer Science. KTH.
- Anton Osika. 2015. Statistical analysis of online linguistic sentiment measures with financial applications. Master’s Thesis in Applied and Computational Mathematics. KTH.
- Andrzej Dudziec. 2015. Searching system for an audio archive. Master’s Thesis in Machine Learning. KTH
- Linda Eriksson. 2014. Better Aggregation of Features in Text. Magisteruppsats i datalogi. KTH.
- Amaru Cuba Gyllensten. 2014. Automatic Lexicon Extraction on Random Index Word Spaces using Small Seed Lexica. Magisteruppsats i datalogi. KTH. (with Magnus Sahlgren)
- Hillevi Hägglöf. 2014. Automatic organization of online Swedish political discourse. Magisteruppsats i språkteknologi. Uppsala universitet.
- Jimmy Callin. 2014. The Distribution of Mood: An Exploration of Distributional Compositions in Sentiment Classification. Kandidatuppsats i språkteknologi. Uppsala universitet. (with Joakim Nivre)
- Martin Bohman and Emelie Kullmann. 2014. Distributionell karaktär hos vissa kategorier av ord. Kandidatuppsats i datalogi. KTH. (with Hedvig Kjellström)
- Markus Östberg. 2013. Subtopic extraction using graph based methods. Magisteruppsats i datalogi. KTH.
- Maria Gerontini. 2013. Geospatial analysis on mobile application usage. Magisteruppsats i datalogi. KTH.
- Gabriel Isheden. 2013. Diagnostics of Semantic Word Spaces. Kandidatuppsats i datalogi. KTH. (with Magnus Sahlgren and Hedvig Kjellström)
- Ariel Ekgren and David Nilsson. 2013. Topology and Word Spaces. Kandidatuppsats i datalogi. KTH. (with Magnus Sahlgren and Hedvig Kjellström)
- Pelle Almquist. 2011. Experiments to Investigate the Utility of Linguistically Informed Features for Detecting Textual Plagiarism. Magisteruppsats i datalogi. KTH. (with Magnus Sahlgren)
- Djuna Franzén. 2006. ``Det är klart det är lättare när man är flera!'' : en undersökning av samarbete inom informationssökning och tilltro till dokument på Internet. Magisteruppsats i biblioteksvetenskap, Uppsala universitet.
- Åsa Johnson. 2006. Tillit på webben -- Annozilla som förtroendeingivande verktyg. Magisteruppsats i biblioteks- och informationsvetenskap. Högskolan i Borås.
- Marcus Ericsson. 2005. Representation av text med semantiska vektorrumsmodeller. Magisteruppsats i språkteknologi, Uppsala universitet. (with Magnus Sahlgren)
- Jon Holmlund. 2004. Translations as Reference for Vector Space Reduction. Magisteruppsats i datorlingvistik, Stockholms universitet. (with Magnus Sahlgren)
- Auri Paajanen. 2002. Possibilités d'un repérage automatique des plans de texte en français. Pro Gradu, Romaanisten kielten laitos. Helsingin yliopisto. (with Andrew Chesterman).
- Eva-Marie Eklund. 2001. Utveckling av en webbapplikation för hantering av sökfrågeexpansion Examensarbete vid Ålands yrkeshögskola, Mariehamn.
- Saija Metsola. 2001. Recognising arguments in argumentative texts. Pro Gradu, Yleisen kielitieteen laitos. Helsingin yliopisto.
- Stina Nylander. 2000. Statistics and Graphotactical Rules in Finding OCR-errors. Magisteruppsats i språkteknologi, Uppsala universitet.
- Niklas Frost and Lars Jonsson. 1999. DIVERSE-Ett talgränssnitt till en Virtual Reality-miljö Magisteruppsats i datavetenskap, Linköpings universitet. (with Ivan Bretan)
- Anette Hulth and Anna Jonsson. 1999. An Experimental Digital Library Platform – A Demonstrator Prototype for the DigLib Project at SICS. Magisteruppsats i data- och systemvetenskap, Stockholms universitet.
- Christina von Löbbecke and Emilie Wiklund. 1999. Konsten att översätta --- en utvärdering av datorstödd översättning. Kandidatuppsats i data- och systemvetenskap, Stockholms universitet.
- Anders Hallberg. 1999. Visualisering och manipulering av genreklassificerade sökresultat. Magisteruppsats i datalogi. Kungliga tekniska högskolan. (with Ivan Bretan).
- Johan Dewe. 1998. En prototyp för att klassificera dokument från WWW med avseende på genre och ämne. Magisteruppsats i datalogi. Kungliga tekniska högskolan. (with Ivan Bretan).
- Aggis Simaiforidis. 1998. Creating a Collaborative Task-Specific Information Retrieval System. Magisteruppsats i systemvetenskap, Uppsala universitet. (with Anna-lena Ereback).
- Preben Hansen. 1997. An exploratory study of IR interaction for user interface design. An interdisciplinary approach. Magisteruppsats i informationsvetenskap, Borås högskola.
- Pär Mattsson. 1996. A Statistical Translation Tool with Aligned Texts. Magisteruppsats i datavetenskap, Uppsala universitet. (with Björn Gambäck).
- Fahima Polly Hussain and Ioannis Tzikas. 1995. Ordstatistisk kategorisering av text för filtrering av elektroniska meddelanden Kandidatuppsats i data- och systemvetenskap, Stockholms universitet.
- Naoufel Ben Cheikh and Magnus Zackrisson. 1994. Genrekategorisering av text för filtrering av elektroniska meddelanden Kandidatuppsats i data- och systemvetenskap, Stockholms universitet. Stockholm University.
- Magnus Nordström and Paul Petterson. 1993.Dilemma -- A tool for rapid manual translation. Magisteruppsats i datavetenskap, Uppsala universitet.