27th Conference of the European Association for Computer Assisted Language Learning

28-31 August 2019, Louvain-la-Neuve, Belgium

First call for papers – EUROCALL 2019

We are very happy to announce that the 27th EUROCALL conference will be hosted by UCLouvain – in collaboration with KU Leuven – in Louvain-la-Neuve (Belgium), from Wednesday 28 to Saturday 31 August 2019.

The 2019 conference theme is CALL and complexity. We will collectively embrace the challenges expressed through the theme: the complexities of languages as such, the complexities of learning and teaching languages, and the added complexity that comes with doing so in technology-mediated contexts. We look forward to discussing all of these with the EUROCALL community!

Key thematic strands include:

CALL for social inclusion
CMC and telecollaboration
Corpora and language learning
Digital bi- and multi-literacies
Intelligent CALL (ICALL)
Mobile assisted language learning (MALL)
Natural language processing applications in CALL
Open Educational Resources and practices (incl. LMOOC)
Research trends in CALL
SLA principles in CALL
Task complexity in CALL
Teacher education and professional development in CALL
The complexity, accuracy, fluency (CAF) framework of proficiency in CALL (research and applications)
Virtual Reality and gamification in language learning

We welcome proposals from researchers and practitioners working in CALL in any areas relevant – but not restricted to – the proposed conference thematic strands. The conference language is English and all proposals for Papers, Symposia, European Projects, Workshops and Posters should ideally be submitted in English.

Important Dates

Call for papers Announcement starts November 2018
Submissions open December 2018
Submissions due 15 February 2019
Notification of acceptance 15 April 2019
Registration Online registration opens February/March 2019
Deadline for early-bird registration 15 May 2019
Deadline for presenters 01 June 2019
Deadline for normal registration 31 July 2019
Late registration starts 01 August 2019
Conference Preliminary programme online June 2019
Full programme online July 2019
Main conference 28-31 August 2019

Presentation categories include

  1. Individual papers

Papers should be submitted for 30-minute presentations. This timing allows for 20 minutes presenting, 5 minutes for questions, and 5 minutes for room changes.

Three types of papers may be given:

Research: papers focusing on a clearly specified research topic supported by a rationale, including a brief literature review. The thrust may be empirical or theoretical. The methodology should be clearly outlined as well as the actual or potential findings.

Research and Development: papers focusing on the development of pedagogies, programmes and projects in technology-rich environments. The research should be original and may emphasise practice rather than research.

Reflective Practice: practice-oriented papers dealing with the integration of technologies in different contexts and for different purposes. The reflection could take the form of evaluation or action-research. Proposals should include elements that are of relevance beyond the context of the practice described

  1. Symposia

Symposia consist of three or four papers on a similar topic, proposed and organised by a chairperson, and should normally address the conference theme. Sessions last for 90 minutes, with NO changeover during the symposium. The proposal should outline the purpose of the symposium, the names and institutions of the participants, with a sentence mentioning what aspect of the main problem that each will address.
Submissions for symposia from EUROCALL SIGs are particularly welcome, with a view to promoting their work to the conference delegates and encouraging participation in the SIGs. Current EUROCALL SIGs are: Teacher Education, Virtual Worlds and Serious Gaming, iCALL, CorpusCall, Computer Mediated Communication, Less-widely Taught Languages, Mobile-Assisted Language Learning, Graduate Students, LMOOC.

  1. European Projects

This year’s conference will again offer a forum for the showcasting and dissemination of EU-funded projects. Each project will be allocated a 30-minute slot, including questions.

  1. Posters

Since posters aim to attract attention to a particular project or research domain, they should mainly focus on work in progress. They may, however, report previous or preliminary findings. Posters should be clear, easy to read and attractively laid out. Submissions from advanced students are especially welcome in this category. A prize will be awarded for the best poster in two categories: PhD/Graduate student and Researcher.

  1. Pre-conference workshops

A limited number of pre-conference workshops will be organized on Wednesday 28 August in the morning. They can either last for 90 minutes or 3 hours. They typically involve a hands-on session, where participants have the opportunity to become familiar with the latest developments in relevant topic areas in language teaching and learning and tools associated with these. The proposal should include the intended duration of the workshop, its main purpose, and a brief outline of topics and activities covered, as well as technical requirements.

Format of abstracts

All presentation categories require the submission of an abstract that does not exceed 500 words, excluding the title, names and affiliations. You will have to select from a list of conference subthemes when submitting your abstract (submissions will be possible round mid-December), which will hopefully help us organize the programme around various thematic strands. You will also be asked to provide 3 or 4 keywords.

How to submit your proposal

The submission platform will be open round mid-December and detailed information will be included in the second call for papers.

Contact information

Any queries relating to the conference should be sent to eurocall2019@uclouvain.be

On behalf of the EUROCALL 2019 organizing team

Fanny Meunier (CECL, UCLouvain)
Conference Chair

Serge Bibauw (ITEC, KU Leuven & CENTAL, UCLouvain)
Frederik Cornillie (ITEC, KU Leuven)
Sylvie De Cock (CECL, UCLouvain & Université Saint-Louis)
Piet Desmet (ITEC, KU Leuven)
Cédrick Fairon (CENTAL, UCLouvain)
Thomas François (CENTAL, UCLouvain)
Germain Simons (Université de Liège)
Anaïs Tack (CENTAL, UCLouvain & ITEC, KU Leuven)
Julie Van de Vyver (CECL, UCLouvain)

International Workshop on the L1 and L2 Acquisition of Information Structure

25-26 April 2019, Leuven, Belgium

The aim of this workshop is to gather researchers working on different aspects of the L1 and L2 acquisition of Information Structure in different languages, using experimental protocols or corpus research, to gain a better understanding of the development of Information Structure.

Call for Papers:

In recent years, the study of Information Structure in child language has gained significant interest. Studies show that the accessibility level of referents influences children’s referential choices (Hendriks, Koster, & Hoeks, 2014; Hickmann & Hendriks, 1999) or word order (Narasimhan & Dimroth, 2008, 2018; Stephens, 2010; Schelletter and Leinonen; 2003). Children’s prosodic and syntactic choices to encode the topic and focus have also been studied in some detail (Arnhold, Chen, & Järvikivi, 2016; Chen, 2011; De Cat, 2009).

While some studies suggest that morphology and syntax are acquired before pragmatics and Information Structure (Schaeffer & Matthewson, 2005), others show that some of children’s constructions encode an adult-like Information Structure configuration: French and Italian children use dislocations to encode the topic of the utterance from the start(Belleti and Manetti, 2018; De Cat, 2007, 2009).

Children do not develop all aspects of Information Structure at the same rate. Dutch children acquire the intonation contour to mark topic before the contour for focus (Chen, 2011), and Portuguese children acquire the syntactic marking of focus while they still struggle with the computations required to interpret stress shift as a focus marker (Costa and Szendrői, 2006). Besides, research suggests that the comprehension of focus-marking intonation is acquired after production in child language (Szendrői, 2004; Gualmini et al., 2003; Paterson et al., 2003, but see Szendrői et al., 2018; Chen, 2010 for a different point of view).

The study of L2 acquisition of Information Structure has also developed recently (Colonna et al., 2018; Park, 2018 among others), and reevaluates former findings. According to Fuller and Gundel (1987), the interlanguage of L2 learners is characterized by an early topic-prominent stage and a late subject-prominent stage, but recent research however suggests a transfer from L1 characteristics (Jin, 1994; Jung, 2004). Some authors consider that L2 learners have difficulties acquiring the syntax-pragmatic and Information Structure interface (Sorace & Filiaci, 2006; Alvaro, 2018). Some find that L2 learners, as they become more advanced, manage to acquire syntactic constructions with the appropriate Information Structure function (Reichle and Birdsong, 2013; Hughes, 2010; Dominguez and Arche, 2010; Donaldson, 2011a, 2011b)

The questions which can be addressed include, but are not restricted to:

– Which prosodic, morphologic or syntactic means are used by children to encode Information Structure? What is the developmental pattern of these means?
– Are some means to encode Information Structure (prosody vs syntax) acquired earlier than others?
– How does the division of labor between syntax/prosody and Information Structure in the target language impact on its acquisition?
– Are some aspects of Information Structure (referential vs. relational) easier to acquire by children?
– Are there early stages in L1 or L2 language development exhibiting more topic-prominent or subject-prominent characteristics?
– Which aspects of Information Structure are acquired in production before comprehension?

We invite you to submit proposals for 20-minute individual presentations. Abstracts should not exceed two pages in length, 12-point type, Times New Roman, single line spacing, 2.5cm (1 inch) margins, including examples and tables.

Abstracts should be submitted in PDF format via EasyChair: https://easychair.org/conferences/?conf=ais2019

Conference Website:


Keynote Speakers:

Aoju Chen (Utrecht Institute of Linguistics)
Carla Soares (Université Paris VIII)
Maria Lobo (Universidade Nova de Lisboa)
Kriszta Szendrői (University College London)

The Syntagmatic Properties of Complementation Patterns: Accommodating Lexical and Grammatical uses of CTP-clauses

09-10 May 2019, Liège, Belgium

Recently, much attention has gone to lexical versus grammatical uses of complement-taking predicate (CTP) clauses (Boye & Harder 2007, 2012; Davidse et al. 2015; Van linden et al. 2016). Concomitant with this, the question has been raised whether these two uses should receive a different structural analysis. Complement clauses of lexical uses have been analysed as subordinate to the CTP-clause. In (1), e.g., the that-clause is typically analysed as the direct object of the main verb; in (4), the that-clause is traditionally analysed as an extraposed subject clause (cf. Quirk et al. 1985: 1224–1225; Huddleston and Pullum 2002: 1252–1254). Semantically, the complement clauses in (1) and (4) are viewed as only secondary. What is discursively primary is the specific emotional state conveyed by the CTP-clauses. The that-clauses represent the proposition presupposed in the processes of regretting (1) and feeling wonder (4) (Van linden et al. 2016).

(1) This was Rosie at her most Rosieish, and Liz only regretted that Pritch wasn’t there to appreciate just what she was up against. (WB)
(2) He spoke out after pro-Agreement parties were presented with the proposals. “I think it is clear that all of the issues have to be addressed,” he said. (WB)
(3) Alain Prost proved you can take time out and make a great comeback when he won his fourth world crown […]. There is no doubt the constant testing and pressure of racing takes a hell of a lot out of you. (WB)
(4) My kids got to see that my out-of-home life was far more complex and intense than they thought. It was a wonder to them that I get to do all this stuff. (IC)

While syntagmatically lexical uses of CTP-clauses are viewed as having ‘complementizing’ status, grammatical uses (2)-(3) are argued to show ‘modifying’ status (Boye & Harder 2007: 568), as the CTP cannot impose its semantic profile on the complement clause (cf. Langacker 1987: 309). The complement clauses contain the main information, and the main clauses are viewed as stance markers or interpersonal modifiers (McGregor 1997: 236). That is, (3) does not describe an act of not doubting. Rather, the impersonal CTP-clause there’s no doubt expresses the speaker’s epistemic stance towards the proposition coded by the that-clause; it signals a high degree of certainty (Davidse et al. 2015: 51). In (2), the personal CTP-clause I think functions as a speech act modifier, hedging the claim in the complement clause (cf. Nuyts 2009: 152). Both CTP-clauses are not part of what is asserted and hence cannot be challenged (Boye & Harder 2007: 573).

This workshop aims to focus on functional approaches towards complementation patterns, and invites contributions discussing the following questions:

– What makes CTP-clauses prone to shift from complementizing to modifying uses? Which semantic types of complement construction (e.g. factive constructions?) do not allow for this shift?
– Does the formal type of complement bear on the possibility of the CTP-clause to have either complementizing or modifying status?
– Does the semantic type of complement (e.g. State of Affairs vs. proposition) bear on the possibility of the CTP-clause to have either complementizing or modifying status?
– Do complement constructions with impersonal matrices (like (3)-(4)) manifest the same structural and functional parameters and shifts as personal CTP-clauses (2)?
– Do lexical uses of CTP-clauses always diachronically precede grammatical uses?
– What does prosody tell us about syntagmatic relationships?

Invited speakers: Kasper Boye (University of Copenhagen), Gunther Kaltenböck (University of Graz) and William McGregor (Aarhus University)
Organizers: An Van linden (Liège), Lieselotte Brems (Liège), Kristin Davidse (Leuven), Lieven Vandelanotte (Namur)

Call for Papers:

We invite 500-word abstracts addressing any of the above issues or related questions, for 20 minute-presentations (+ 10′ discussion time). Abstracts should be submitted to an.vanlinden@uliege.be, and should contain title, author’s name and affiliation.

Deadline: 20 December 2018
Notification: 15 February 2019

Job: Research professor, Linguistic pragmatics, University of Antwerp

University or Organization: University of Antwerp
Department: Department of Linguistics
Job Location: Antwerp, Belgium
Web Address: https://tinyurl.com/y95brwfo
Job Title: Research professor, Linguistic pragmatics
Job Rank: Assistant Professor

Specialty Areas: Anthropological Linguistics; Pragmatics; Sociolinguistics; Multilingualism; Urban Studies


The assignment consists of lecturing duties, scientific research and academic service to society. During a period, limited to five years (duration of the temporary appointment in tenure track), scientific research will be the main activity.

– You will expand on scientific research into concrete instances of language use within multilingual urban and institutional contexts, and frame this research as part of a project of theory formation in pragmatics.
– You will acquire and manage external funding (national and international).
– You will supervise doctoral students.
– You will offer scientific and other services, including administration and other forms of organizational coordination and support.
– You will teach a course on pragmatics: language and the city in the Master of Linguistics.

Profile and requirements:
– You hold a doctorate degree (PhD) in linguistics or a doctoral degree of equal value.
– You have a minimum of 2 years of experience on the postdoctoral level at the closing date of the vacancy.
– You have demonstrable expertise in ethnographic and possibly interdisciplinary approaches to sociolinguistic research topics, preferably strongly empirically driven and paying particular attention to phenomena of (urban) multilingualism.
– You study topical issues in linguistic pragmatics from a global perspective.
– You have an international academic CV and you conduct qualitatively outstanding academic research within the given domain.
– Your academic qualities comply with the requirements stipulated in the university’s policy.
– The focus in your teaching corresponds to the educational vision of the university.
– You have leadership skills (or the potential to develop them).
– You are quality-oriented, conscientious, creative and cooperative.
– If you do not have Dutch, the administrative language of the university, as your native language, you should be willing to obtain a CEFR B2 level of proficiency in Dutch within five years of appointment. As soon as you take on teaching duties as a course unit coordinator, you should be able to demonstrate a CEFR C1 level of proficiency in the language of instruction. The University of Antwerp supports international staff members on an integration trajectory and offers tailor-made language coaching in compliance with Flanders’ statutory language regulations.

We offer:

A full-time position as a lecturer in a temporary appointment in the tenure track system for a term of five years. This position will lead to an immediate permanent appointment as a senior lecturer if the performance is assessed favourably on the basis of previously determined and publicly announced evaluation criteria. After the permanent appointment another period of five years is given with limited lecturing duties in order to strengthen the research curriculum;
in case of equal qualifications, priority will be given to candidates of the underrepresented gender within the domain of science.
This priority is not automatic nor unconditional, as the evaluation will always take into account the personal situation of every candidate;
the date of appointment will be 1 October 2019 at the earliest;
a gross monthly salary as a full-time lecturer ranging from € 4.255,06 to € 6.272,13;
an attractive starter package consisting of a full four-year PhD project and consumables (€30 000);
a dynamic and stimulating work environment.

How to apply?
Applications may only be submitted online, until the closing date 21 January 2019. More information can be found on our website via the application link provided below.

Application Deadline: 21-Jan-2019

Web Address for Applications: https://www.uantwerpen.be/en/jobs/vacancies/ap/2018zapflwex332/
Contact Information:
Frank Brisard
Email: frank.brisard@uantwerpen.be

Language in Webcare: Interdisciplinary Perspectives

22-Nov-2018 – 23-Nov-2018, Ghent, Belgium

With the rise of digital business communication, end-users of products and services can now easily communicate positive and negative feedback to other customers and organizations on social networking and (micro)blogging sites, the sheer amount of which is hard for corporations to monitor, let alone respond to. As negative word-of-mouth on both the issue at hand and the way it has been tackled may have detrimental consequences in terms of reputation and sales (Luo 2009), organizations now have to access these social platforms as well and engage in a very delicate type of online service encounter (i.e. webcare) with the prime intention of nursing customer relationships and monitoring reputation management (Van Noort and Willemsen 2011). The success of this type of interaction depends on many different aspects, including the linguistic realization of both the original message by the customer and the ensuing webcare itself. However, context-specific knowledge on what constitutes the most appropriate, effective communicative strategies during critical moments – both from the customers’ and the companies’ perspective – is lacking (Lee and Song 2010) or proves to be somewhat contradictory.

As organizers of this symposium, we believe that research into the communicative challenges of digital business communication would greatly benefit from an interdisciplinary approach, combining theories and methods from linguistics, service-oriented marketing and public relations (see also Holmqvist et al. 2017; Carnevale et al. 2017). Therefore, this symposium aims to bring together scholars in language, communication and marketing studies who all share an interest in the linguistic and communicative intricacies of online service management. We invite papers focusing on consumer reviews, complaints, webcare and/or crisis communication from different theoretical and methodological perspectives.

We invited five speakers with an expertise in discourse- and communication-related approaches to online consumer complaints, reviews, and webcare: Camilla Vasquez (University of South Florida), Valerie Creelman (Saint Mary’s University), Guda Van Noort (University of Amsterdam), Rob Le Pair (Radboud University Nijmegen), An-Sofie Claeys (University of Leuven).

We ask scholars attending the conference (except for BA and MA students) to pay a registration fee of 100€ (excluding dinner on November 22).

For further information please contact sofie.decock@ugent.be, bernard.declerck@ugent.be and/or rebecca.vanherck@ugent.be.


The program can be found on: http://www.webcare2018.ugent.be/programme/

Job : Swedish Computational Linguist, Acapela Group (Mons, Belgium)

We are looking for a Swedish Computational Linguist.

The candidate will be part of a team that designs, develops, tests, and deploys Text-To-Speech technologies supporting a range of products and services in a large portfolio of languages. With other members of the team, he/she will be able to develop advanced solutions that will help a large number of people around the world.

Job description:
• New languages/voices development
• Linguistic services
• Update linguistic components/data

• A degree in Computational Linguistics
• Native Swedish, additional Nordic languages are an asset
• Fluent in English
• Good scripting language knowledge (like Python/Perl)
• Curiosity about phonetics and languages
• Working knowledge of Windows and/or Linux
• Team player with good interpersonal skills
• Strong commitment to the job

About Acapela Group
Acapela Group brings together talented people from very different backgrounds and areas of expertise, resulting in a rich cultural and multilingual environment. We work on voices and languages, we look at the whole world and all application fields to help us create authentic and genuine voices that change or simplify people’s daily lives.

URL: https://www.acapela-group.com/about-us/jobs/swedish-computational-linguist-text-to-speech/

Job : Gestionnaire de corpus de données, UCLouvain

L’Université catholique de Louvain recherche un (h/f) gestionnaire de données

  • à temps partiel (50%) pour une durée déterminée de 18 mois (avec possibilité de prolongation)
  • pour l’Institut langage et communication (ILC), du Secteur des sciences humaines (SSH) – à Louvain-la-Neuve
  • entrée en fonction: immédiate


La recherche actuelle fait un usage massif de données langagières écrites et orales, dans différentes langues (français, espagnol, anglais, néerlandais, etc.). Pour être exploitables, ces données langagières doivent être documentées (métadonnées), anonymisées (afin de respecter les règles sur les donnéespersonnelles), enrichies d’annotations (transcription, indexation, analyse thématique, etc.) et déposéesdans des bases de données interrogeables en ligne. C’est à ces différentes tâches que le·la gestionnaire de données contribuera au sein de l’Institut Langage et Communication (ILC), et plus particulièrement dupôle de recherche en linguistique (PLIN) et de la plateforme CENTAL (Centre de Traitement automatique du langage).


En collaboration avec les chercheurs de ILC/PLIN, le·la gestionnaire de données a pour fonctions de :

  • Superviser la chaine de traitement de constitution des corpus oraux et écrit (acquisition des données, documentation des métadonnées, transcriptions et annotations, versement dans les bases de données existantes, standardisation des formats utilisés)
  • Développer des outils de prétraitement et de traitement des données (segmentation, alignement du texte au son, alignement texte-texte, annotation automatique ou semi- automatique, etc.)
  • Assurer une veille technologique pour l’interopérabilité des données (documentées et traitées selon les standards internationaux, cf. Clarin, Ortolang, Olac, etc.) et l’amélioration de l’acquisition des données (automatic speech recognition, tokenisation, etc.)
  • Veiller au respect des conventions juridiques et éthiques liées à la protection des données (RGPD)
  • Représenter l’UCL dans différents consortiums internationaux des données en linguistique.Qualifications et aptitudes requises

    Le·la candidate répondra aux qualifications suivantes :

    • titulaire d’un diplôme de Master en Linguistique, Finalité spécialisée en Traitement automatique

      du langage, ou équivalent

    • compétences de programmation : Perl et/ou Python, bonne connaissance du XML
    • capacité à traiter des données langagières dans plusieurs langues (français, anglais, néerlandais,

      espagnol, allemand, etc.)

    • connaissance de l’anglais (B2) et en particulier de l’anglais académique (pour participer à des

      réunions internationales et contribuer aux publications de recherche)

    • sens du travail en équipe, capacité d’écoute et d’analyse des besoins, réactivité

Votre candidature

(lettre de candidature, curriculum vitae, photo récente en format d’identité) est à transmettre :Par e-mail (de préférence) à l’adresse : anne-catherine.simon@uclouvain.be

OU par la poste, à l’adresse:

Université Catholique de Louvain
Institut Langage et Communication (ILC) Anne Catherine SIMON
Place Blaise Pascal, 1 – Boite L3.03.33 B-1348 Louvain-la-Neuve

CogLing8 programme and registration

Dear colleague,

We are pleased to announce you that the registration for CogLing8 is now open. We kindly request you to register before 15 November through the following link (also available via the conference’s webpage): https://docs.google.com/forms/d/e/1FAIpQLSdlEROqzjyA44yVDQB7pQxTD60cNFJwlN0y8A-UNmgh3GQxrQ/viewform?usp=sf_link

A provisional programme is now available on the conference website https://cogling2018.wordpress.com/

It is still possible to book a hotel room at the university rate via the link provided on our website https://cogling2018.wordpress.com/travel-and-accommodation/. Please note that it is compulsory to use the link and form mentioned on this page in order to obtain the university rate. A limited number of rooms is available in both hotels (please note that the offer for the Ibis hotel is valid only for bookings made before 12 November). Our website also includes a link to other accommodation options in the numerous B&Bs in Louvain-la-Neuve, as well as travel information.

Kind regards,

The organizing committee

Barbara De Cock, Liesbeth Degand, Gaëtanelle Gilquin, Sara Jonkers, Julien Perrez, Kristel Van Goethem

Advance notice: ‘Corpus Linguistics with R’ and ‘Statistics for linguistics with R’ bootcamps by S.T. Gries

Louvain-la-Neuve, Belgium, August 2019

The Linguistics Research Unit of the Institute of Language and Communication (Université catholique de Louvain, Belgium) will be hosting two 30-hour bootcamps by Stefan Gries next summer.

The ‘Corpus Linguistics with R’ bootcamp (12-16 Aug 2019) is a hands-on introduction to using the programming language R for the analysis of textual data (mostly corpora, but theoretically also literary works, web data, etc.). It is based on the second edition (2016) of Gries’s textbook Quantitative corpus linguistics with R and introduces a variety of programming constructs required for text processing and corpus exploration including

  • building word frequency lists and computing type-token ratios;
  • computing dispersion and key words statistics;
  • extracting concordance lines.

For that, we will discuss different relevant functions and data structures, control flow structures such as loops and conditionals, and a sizable number of regular expressions; in addition and time permitting, we will also cover very elementary basics of data visualization. The kinds of data dealt with in this course come from a variety of differently formatted/annotated corpora and will also include 1-2 examples of literary works and/or XML processing.

The ‘Statistics for linguistics with R’ bootcamp (19-23 Aug 2019) is a hands-on introduction to statistical methods for both graduate students and seasoned researchers and is based on the second edition (2013) of Gries’s textbook Statistics for linguistics with R. The course is intended for linguists who already have a basic knowledge in statistics and some experience using R, and who wish to improve their proficiency in statistical analysis of linguistic data. Using the open source software and programming language R, we will:

  • briefly recap basic aspects of statistical evaluation as well as several descriptive statistics;
  • briefly discuss a selection of monofactorial statistical tests for frequencies, means, correlations and how they constitute special (limiting) cases of regression methods;
  • explore different kinds of multifactorial and multivariate methods, in particular different kinds of regression approaches (fixed-effects only and mixed-effect modelling) as well as classification trees and random forests.

Details about the previous edition of the ‘Statistics for linguistics with R’ bootcamp in LLN are available at: https://uclouvain.be/en/research-institutes/ilc/cecl/rling2017.html. For info about the prerequisites, visit https://uclouvain.be/en/research-institutes/ilc/cecl/prerequisites.html.

The website of the two events will be online in early 2019 and online registration will start on 1 March 2019. It will be possible to register for one event only but priority will be given to people who register for both. The number of participants is limited. If you would like to participate, mark the date in your diary!

Contact email: magali.paquot@uclouvain.be

Magali Paquot

6th International Conference on Statistical Language and Speech Processing

October 15-16, 2018, Mons, Belgium

Co-organized by:

NUMEDIART Institute, University of Mons
LANGUAGE Institute, University of Mons
Institute for Research Development, Training and Advice (IRDTA), Brussels/London

Website: http://slsp2018.irdta.eu/


Monday, October 15

09:00 – 09:30 Registration

09:30 – 09:40 Opening

09:40 – 10:30 Thomas Hain. Crossing Domains in Automatic Speech Recognition – Invited lecture

10:30 – 11:00 Break

11:00 – 12:15

Amal Houidhek, Vincent Colotte, Zied Mnasri and Denis Jouvet. DNN-based Speech Synthesis for Arabic: Modelling and Evaluation

Antoine Perquin, Gwénolé Lecorvé, Damien Lolive and Laurent Amsaleg. Phone-level Embeddings for Unit Selection Speech Synthesis

Raheel Qader, Gwénolé Lecorvé, Damien Lolive and Pascale Sébillot. Disfluency Insertion for Spontaneous TTS: Formalization and Proof of Concept

12:15 – 13:45 Lunch

13:45 – 14:35 Simon King. Does ‘End-to-End’ Speech Synthesis Make any Sense? – Invited lecture

14:35 – 14:50 Break

14:50 – 16:05

George Christodoulides. Forced Alignment of the Phonologie du Français Contemporain Corpus

Ruei Hung Alex Lee and Jyh-Shing Roger Jang. A Syllable Structure Approach to Spoken Language Recognition

Gueorgui Pironkov, Sean Wood, Stéphane Dupont and Thierry Dutoit. Investigating a Hybrid Learning Approach for Robust Automatic Speech Recognition

16:05 – 16:20 Break

16:20 – 17:30 Poster session I

17:30 – 19:30 Touristic visit

Tuesday, October 16

09:00 – 09:50 Isabel Trancoso. Analysing Speech for Clinical Applications – Invited lecture

09:50 – 10:20 Break

10:20 – 11:35

Jan Vanek, Josef Michalek, Jan Zelinka and Josef Psutka. A Comparison of Adaptation Techniques and Recurrent Neural Network Architectures

Andris Varavs and Askars Salimbajevs. Restoring Punctuation and Capitalization Using Transformer Models

David Awad, Caroline Sabty, Mohamed Elmahdy and Slim Abdennadher. Arabic Name Entity Recognition Using Deep Learning

11:35 – 11:50 Break and Group photo

11:50 – 13:05

Pratik Doshi and Wlodek Zadrozny. Movie Genre Detection Using Topological Data Analysis and Simple Discourse Features

Daniel Grießhaber, Thang Vu and Johannes Maucher. Low-resource Text Classification Using Domain-adversarial Learning

Manny Rayner, Johanna Gerlach, Pierrette Bouillon, Nikolaos Tsourakis and Hervé Spechbach. Handling Ellipsis in a Spoken Medical Phraselator

13:05 – 14:35 Lunch

14:35 – 15:50

Laura García-Sardiña, Manex Serras and Arantza Del Pozo. Knowledge Transfer for Active Learning in Textual Anonymisation

Fernando Gomes and Juan Manuel Adán-Coello. Studying the Effects of Text Preprocessing and Ensemble Methods on Sentiment Analysis of Brazilian Portuguese Tweets

Daniel Lichtblau and Catalin Stoean. Text Documents Encoding through Images for Authorship Attribution

15:50 – 16:05 Break

16:05 – 17:05 Poster session II

17:05 – 17:15 Closing