Home

We have two available PhD positions, funded by the CLEANUP and GraphDial projects! See here and here to apply. Application deadline: August 15 and 16.

We have just started an exciting new project on dialogue modelling and human-robot interaction! The GraphDial project will investigate the use of probabilistic graphs for dialogue management. GraphDial will last for four years and is funded by a Young Research Talent grant from the Research Council of Norway.

The CLEANUP project has now officially started! CLEANUP is a 4-years project funded by the Research Council of Norway and will develop data-driven models to anonymise text documents containing personal information. The project brings together researchers in natural language processing, computational privacy, health informatics and IT law, along with Norwegian public and private organisations.

Long paper accepted to ACL 2020: "Named Entity Recognition without Labelled Data: A Weak Supervision Approach" (joint work with Jeremy Barnes, Aliaksandr Hubin and Samia Touileb).

Together with Michael Riegler (from Simula Metropolitan), I've written a short piece in Morgenbladet to react to recent comments from IKT-Norge on international PhD students.

I have written a short article on ethics and language technology as part of the blog of the Young Academy of norway on forskning.no.

I’m honored to have been elected as a member of the Young Academy of Norway for a period of four years. The Academy is constituted of about 40 young researchers working in Norwegian research institutions. Its main purpose is to serve as the voice of young researchers in the public arena, through a range of initiatives related to research policy and science dissemination.

The SAFERS project has now officially started! SAFERS investigates how speech technology and machine learning can be used to automatically transcribe emergency calls (113 in Norway) and provide real-time analysis and prediction tools to emergency response services. SAFERS is funded by the Norwegian Research Council.

I’m thrilled to start a new position as a senior research scientist at Norsk Regnesentral and am looking forward to working on new exciting projects!

Jörg Tiedemann and I just released a new major release of the OpenSubtitles collection of parallel corpora. The release is compiled from a large database of movie and TV subtitles and includes 2.6 billion sentences across 60 languages! This makes it the world’s largest collection of parallel corpora freely available. See our paper at LREC for more details on the corpus.

My article “A hybrid approach to dialogue management based on probabilistic rules” will soon appear in Computer Speech & Language (see the “Publications” section). The article is essentially a summary of my PhD work and describes the formalisation of probabilistic rules, the statistical estimation of unknown parameters, and the empirical evaluation of the framework in a human-robot interaction domain.

Raveesh Meena and I have written a feature article on spoken dialogue systems for XRDS, the flagship academic magazine for student members of ACM. You can access the full article here.

I am now back in Oslo after a 3-months research stay at the Idiap institute in Switzerland. Up to December, I’ll be lecturing on spoken dialogue systems as part of the INF5820 course on language technology applications.

I am delighted to visit the Idiap research institute in Switzerland for a period of 3 months (from August to October) in order to work together with Andrei Popescu-Belis on dialogue modelling for statistical machine translation.

I successfully defended my PhD thesis on the 21st of February 2014! Thanks to everyone who contributed to this event [1, 2, 3, video]. Starting from next month, I will work as a Postdoctoral Research Fellow for a 3-years project funded by the Norwegian Research Council.

The first public release of the OpenDial toolkit is finally available! OpenDial is a Java-based toolkit to develop robust and adaptive dialogue systems for various domains. The code has recently been fully refactored and includes an easy-to-use graphical interface. The project website also features a user manual for the toolkit.

My PhD defense is officially scheduled for Friday, 21st February 2014 at 14:15 (see here for all practical details). I’m honoured to have Kristiina Jokinen, Verena Rieser and Tørresen as opponents. Everybody is welcome to attend!

My 3-years postdoctoral project on “Dialogue Modelling for Statistical Machine Translation” has been selected for funding by the Norwegian Research Council! Competition was quite tough (around 10% acceptance rate).

Big news! After months of hard work, I finally submitted my PhD thesis this Thursday, 31st October 2013. The PDF is available here. Now, off to a week of well-deserved vacation ;-)

A-magasinet featured this week a three-pages article on Lenny and my research on human-robot interaction through spoken dialogue.

My paper on model-based Bayesian reinforcement learning for dialogue management has been accepted for the upcoming http://www.interspeech2013.org/ Interspeech conference (see the “Publications” section). I have also updated the media section with new material.

Please come to the Forsker Grand Prix show at the Sentrum Scene on Tuesday 25/09/2012… and vote for me, of course ;-)

My paper on “Probabilistic Dialogue Models with Prior Domain Knowledge” (see publications page) has been accepted as a full talk to SIGDIAL 2012, which is going to take place on July 5-6 in Seoul, South Korea.

If you are a young researcher working in the field of spoken dialogue systems, please consider participating to the Young Researchers’ Roundtable on Spoken Dialogue Systems, which is organised just before SIGDial.

The proceedings of the EACL Student Research Workshop 2012 (which I have had the pleasure of co-chairing along with Mattias Nilsson and Marta Recasens) are now fully available online in the ACL anthology.

Back from Portland (Oregon) where I presented my paper on “Multi-policy Dialogue Management” (see publications page).