The 7th annual CLT workshop brings together researchers in language technology and computational linguistics from the University of Gothenburg and Chalmers. We will exchange research results and ideas, discuss the future of CLT, and (last but not least) socialize.


Thursday 30/11

  • 09.00 embark on bus at Olof Wijksgatan 6 (outside FLoV)
  • 09.15 bus leaves
  • 10.45 bus arrives at Gullmarsstrand
  • 10.45-11.15 coffee
  • 11.15-12.00 welcome + presentation session (2 talks; chair: Staffan Larsson)
    • Elena Volodina: SweLL - an upcoming infrastructure for Swedish as a Second Language
    • Dan Rosén: The SweLL normalization editor for learner texts
  • 12.00 lunch
  • 13.20-14.20 presentations (3 talks; chair: Gerlof Bouma)
    • Yuri Bizzoni and Shalom Lappin: Predicting Gradient Metaphor Paraphrase Judgments with a Composite DNN
    • Jacobo Rouces: Sentiment Analysis in Swedish
    • Simon Dobnik: KILLE: a Framework for Situated Agents for Learning Language Through Interaction
  • 14.20-14.30 poster/demo madness (chair: Robin Cooper)
  • 14.30-15.30 poster/demo session 1
  • 15.30-16.10 coffee + check-in
  • 16.10-17.10 presentations (3 talks; chair: Peter Ljunglöf)
    • Ellen Breitholtz and Chris Howes: Incremental Reasoning in Dialogue Involving Patients with Schizophrenia
    • Haris Themistocleous: Deciphering the speech signal: speakers and communities of speakers
    • Robin Cooper: Playing games with types
  • 17.30 Glögg
  • 18.00 Dinner

Friday 1/12

  • before 09.00: check out
  • 09.00-10.00 presentations (3 talks; chair: Jacobo Rouces)
    • Aarne Ranta: Developing a Mobile Translation App for Healthcare
    • Katie Fraser: Detecting cognitive impairment from speech
    • Asad Sayeed: Semantic roles and event knowledge
  • 10.00-10.10 poster/demo madness (chair: Markus Forsberg)
  • 10.10-11.20 poster/demo session 2 + coffe
  • 11.20-11.50 wrap up, discussion, planning (chair: Peter Ljunglöf)
  • 11.50 lunch
  • 13.00 bus leaves Gullmarsstrand
  • 14.30 bus arrives at Olof Wijksgatan 6

Poster/demo session 1 (chair: Robin Cooper)

  • Staffan Larsson: Approaches to compositionality for perceptual meanings
  • Ildikó Pilán: Identifying correction candidates for Swedish learners’ spelling errors
  • Markus Forsberg: Strix: A new bird at Språkbanken
  • Dana Dannélls: Second language learners acquisition of Swedish constructions – A case study
  • Inari Listenmaa: Testing GF grammars
  • Christine Howes: Feedback relevance spaces: The organisation of increments in conversation.
  • Malin Ahlberg: News from Karp - Språkbankens lexical infrastructure
  • Gerlof Bouma and Yvonne Adesam: Eukalyptus treebank of written Swedish
  • Peter Ljunglöf: Interactive correction of speech recognition errors

Poster/demo session 2 (chair: Markus Forsberg)

  • Mehdi Ghanimifard: Spatial Relations in Visually Grounded Neural Language Models
  • Richard Johansson: Introduction to the EPE shared task
  • Richard Johansson: Training Word Sense Embeddings With Lexicon-based Regularization"
  • Herbert Lange: Language Learning with MUSTE
  • Prasanth Kolachina: TBD
  • Vladislav Maraev: Laughter-infused dialogue systems
  • Stergios Chatzikyriakidis: Coq for Natural Language Semantics
  • Sylvie Saget: Cooperative Speaker Revisited


  • Yvonne Adesam, Department of Swedish (Språkbanken)
  • Malin Ahlberg, Department of Swedish (Språkbanken)
  • Yuri Bizzoni, FLoV, CLASP
  • Gerlof Bouma, Department of Swedish (Språkbanken)
  • Ellen Breitholtz, FLoV, CLASP
  • Stergios Chatzikyriakidis, FLoV, CLASP
  • Robin Cooper, FLoV, CLASP
  • Dana Dannélls, Department of Swedish (Språkbanken)
  • Simon Dobnik, FLoV, CLASP
  • Markus Forsberg, Department of Swedish (Språkbanken)
  • Katie Fraser, Department of Swedish (Språkbanken)
  • Mehdi Ghanimifard, FLoV, CLASP
  • Christine Howes, FLoV, CLASP
  • Richard Johansson, CSE
  • Prasanth Kolachina, CSE
  • Herbert Lange, CSE
  • Shalom Lappin, FLoV, CLASP
  • Staffan Larsson, FLoV, CLASP
  • Inari Listenmaa, CSE
  • Peter Ljunglöf, CSE
  • Vladislav Maraev, FLoV, CLASP
  • Bengt Nordström, CSE
  • Ildikó Pilán, Department of Swedish (Språkbanken)
  • Aarne Ranta, CSE
  • Dan Rosén, Department of Swedish (Språkbanken)
  • Jacobo Rouces, Department of Swedish (Språkbanken)
  • Sylvie Saget, FLoV, CLASP
  • Asad Sayeed, FLoV, CLASP
  • Haris Themistocleous FLOV, CLASP
  • Elena Volodina, Department of Swedish, UGOT

Date: 2017-11-30 09:00 - 2017-12-01 14:30

Location: Gullmarsstrand, Fiskebäckskil



The sixth annual Språkbanken Autumn Workshop will be held on the 17th of October. The workshop theme this year is content (semantics).

The language infrastructure of Språkbanken is freely available to all researchers. Our web-based tools can be used to access all kinds of texts, anything from historical and modern newspaper texts, novels and poetry, social media outlets such as blogs and discussion forms. Use our tools to efficiently wade through billions of sentences and produce mesmerising visualisations. At our annual autumn workshop you can try the tools out! We’ll demo the new features, show you how they’re used, and get a discussion going around your particular research questions.

We will start at 13.15 with presentations featuring our research and research infrastructure and finish with some practical exercises combined with demo and poster presentations. This will be followed by a social gathering with some bubbly and snacks.

A programme is available here: https://spraakbanken.gu.se/swe/Om%20oss/hoestworkshop. Note that the workshop language is Swedish. In order to participate in the practical exercises you must bring a laptop, but this is not a requirement for participation in the workshop.

For planning purposes we kindly ask you to register here: https://spraakbanken.gu.se/swe/Om%2520oss/hoestworkshop/registration no later than 9th October if you are planning to attend.


Date: 2016-10-17 13:15 - 18:00

Location: L100, Lennart Torstenssonsgatan 8



We will show the new version of the Swe-Clarin toolbox at an inauguration ceremony. During the course of this day, researchers from different disciplines in digital humanities will talk about their experiences with using language data as primary research data. There will be stations where our tools are presented and a possibility to try them out with guidance. The evening will end with a mingle and refreshments.

You can read more about the event and indicate your interest in participation here: https://sweclarin.se/eng/Inauguration_of_the_Swe-Clarin_toolbox_webform.

Date: 2016-10-07 10:00 - 20:00

Location: Ågrenska villan



Karin Hedberg will defend her MLT masters thesis.

The opponent is Resa Khezri and the examiner is Professor Lars Borin.

Date: 2016-09-29 10:30 - 12:00

Location: T340, FLoV, Olof Wijksgatan 6



The Language Technology research group (Språkbanken https://spraakbanken.gu.se/eng) in the Department of Swedish at the University of Gothenburg, Sweden, invites applications for one (or more) fully funded four-year PhD position(s) in Natural language processing.

Språkbanken has conducted research in NLP and neighboring fields for over 40 years. At present, our work focuses on language technology methodologies for the Swedish language, and the development of linguistic resources and tools for all historical stages of Swedish, in a number of internally and externally funded research projects. A recent but increasingly important area of interest is the application of language technology as a research tool for the humanities and social sciences (digital humanities). In particular, Språkbanken is the national coordinator for the Swedish node of the European CLARIN ERIC.

The deadline for applications is 3rd October 2016. The starting date for the position(s) is 1st February, 2017 (or as soon as possible after this date as per agreement).

See the information for applicants at: https://spraakbanken.gu.se/eng/phd-program.

For more information, you can also contact Lars Borin lars.borin@svenska.gu.se.

Date: 2016-09-12 11:17




The Swedish Language Bank (Språkbanken) has a vacancy for one postdoctoral fellow position in Language Technology specializing in early detection of cognitive abnormalities that precede the onset of dementia

Closing date: September 30, 2016.

For more details about the position and link to the online application system please visit:


Date: 2016-09-09 12:56




Abstract syntax trees are an alternative representation to syntactic structures commonly found in NLP systems. This representation allows for sharing of structures across languages, making it well suited to serve as a translation interlingua. Grammatical Framework is a grammar formalism that captures cross-linguistic generalizations through the use of abstract syntax. The Resource Grammar Library (GF-RGL) in GF implements multilingual grammars for over 30 languages.

Universal Dependencies (UDs) is a parallel effort to use shared structures to analyse sentences in different languages. The set of part-of-speech tags and functions are shared across languages. The linguistic data available from this project is annotated data i.e. sentences annotated with UD structures in over 40 languages.

The main contribution of this thesis is to bridge these two representations: despite the similar motivation behind these two efforts, the representations used vary significantly. Hence, we propose a conversion method to convert the abstract syntax trees in GF to the structures used in UD. We find that the correspondence between GF-RGL and UD is significant, and the differences between the two raise interesting questions about the level of abstraction. We also present practical applications to our method: (1) the use of GF parser as a dependency parser and (2) to bootstrap UD treebanks from GF treebanks.

Another topic addressed in this thesis is the problem of out-of-vocabulary words that comes up in symbolic systems. We address this problem in the context of part-of-speech tagging and statistical dependency parsing. We propose a simple method to use a distributional thesaurus to replace unknown words and show through empirical evaluation that our method improves both overall accuracies and accuracies for unknown words. Our method is generic and can be adapted to fit other NLP systems.

The discussion leader is Filip Ginter, University of Turku.

Date: 2016-09-15 10:00 - 12:00

Location: HC2, Hörsalsvägen 14



(This seminar will be held in Swedish.)

Som en specialinriktning inom logopedi görs undersökningar av språkfunktion hos personer med sviktande eller nedsatt mental förmåga. Kraven på metod är höga och det krävs god förmåga till observation av språkligt och kommunikativt beteende. Undersökningen aktualiseras när en person genomgår minnesutredning p.g.a. misstanke om demenssjukdom och den logopediska insatsen kan då vara en bit i ett stort pussel. På Karolinska Universitetssjukhuset har vi utvecklat och prövat testmetoder för att kunna beskriva patienters språkliga funktion och öka förståelsen av de besvär som patient och/eller omgivning noterat. Ett flertal vetenskapliga studier har genomförts och fördjupat kunskapen om språkliga funktioners samband med tänkande. Ett testbatteri (SLUM) har prövats på ett standardiserat sätt under fem års tid och är nu utvärderat. SLUM presenteras kort och med extra fokus på hur testresultat och observationer kan användas för att beskriva och påvisa avvikande språkligt beteende associerat med sjukdomsdiagnos. Eftersom ett specialintresse är semantik kommer detta vara i fokus.

Ing-Mari Tallberg [1,2]

  1. Funktionsområde Logopedi, Funktion Hälsoprofessioner, Karolinska Universitetssjukhuset, Stockholm, Sweden
  2. Enheten för Logopedi, (CLINTEC), Karolinska Institutet, Stockholm, Sweden

Date: 2016-10-06 10:30 - 12:00

Location: Lennart Torstenssonsgatan 8, L307



The Master's Programme in Language Technology welcomes you to the upcoming thesis defence:

13.00-14.30 Tessa Koelewijn. Thesis: ENTITY RELATION EXTRACTION. Exploring the Use of Coreference Resolution in a Distant Supervision Approach to Automated Relation Extraction
Examiner: Lars Borin
Supervisor: Richard Johansson
Opponent: Sophie Chesney

Date: 2016-06-14 13:00 - 14:30

Location: C430, Humanisten



The Master's Programme in Language Technology welcomes you to the upcoming thesis defences:

10.30-12.00 Wafia Adouane. Thesis: AUTOMATIC DETECTION OF UNDERRESOURCED LANGUAGES. Dialectal Arabic Short Texts
Examiner: Staffan Larsson
Supervisors: Richard Johansson, Nasredine Semmar and Alan Said (Recorded Future)
Opponent: Karin Hedberg

13.00-14.30 Sophie Chesney. Thesis: TF-REL: LINGUISTICALLY MOTIVATED TERM WEIGHTING . From Relevance to Keyword Extraction Examiner: Lars Borin
Supervisors: Simon Dobnik, Magnus Sahlgren
Opponent: Tessa Koelewijn

14.30-16.00 Stian Rødven Eide. Thesis: MEANINGFUL CONNECTIONS. On Prolog, Pengines and the Semantic Web Examiner: Staffan Larsson
Supervisors: Torbjörn Lager, Simon Dobnik
Opponent: Anna Ehrlemark

Date: 2016-06-13 10:30 - 16:00

Location: C430, Humanisten