25 September (Thursday)

[Hotel/conference centre/2nd floor]

18:00-19:00

Registration

19:00-21:00

Welcome reception

 

26 September (Friday)

[Hotel/Alfa hall/2nd floor]

08:00-19:00

Registration desk open

09:00-09:05

Opening of the Conference

09:05-10:00

KEYNOTE - Walter Daelemans:

Machine learning approaches to computational stylometry

10:00-10:30

Coffee break

 

Oral Presentations: Methods in Computational Linguistics

Chair: Gintarė Grigonytė

10:30-10:55

Roberts Darģis and Artūrs Znotiņš: Baseline for Keyword Spotting in Latvian Broadcast Speech

10:55-11:20

Jurgita Kapočiūtė-Dzikienė, Ligita Šarkutė and Andrius Utka: Automatic Author Profiling of Lithuanian Parliamentary Speeches: Exploring the Influence of Features and Dataset Sizes

11:20-11:45

Kadri Muischnek, Kaili Müürisep and Tiina Puolakainen: Dependency Parsing of Estonian: Statistical and Rule-based Approaches

11:45-12:10

Pēteris Paikens: Latvian Newswire Information Extraction System and Entity Knowledge Base

12:10-12:35

Artūrs Znotiņš: Coreference Resolution in Latvian

12:35-13:30

Lunch [hotel/restaurant/1st floor or city centre]

If you wish to have lunch in the hotel restaurant please mark the option in the online registration form. Alternatively you are welcome to have lunch in the city.

13:30-14:30

KEYNOTE - Adam Kilgarriff:

How to Evaluate Corpus

14:30-15:00

Coffee break
 

Oral presentations: Preparation of Language Resources

Chair: Kadri Muischnek

15:00-15:25

Didzis Gosko and Guntis Barzdins : Adding Construction to the Latvian FrameNet
15:25-15:50

Jenna Kanerva, Juhani Luotolahti, Veronika Laippala and Filip Ginter: Syntactic N-gram Collection from a Large-Scale Corpus of Internet Finnish

15:50-16:15

Lauma Pretkalniņa and Laura Rituma: Constructions in Latvian Treebank: the Impact of Annotation Decisions on the Dependency Parsing Performance

16:15-16:40

Inguna Skadiņa, Ilze Auziņa, Guntis Bārzdiņš, Raivis Skadiņš and Andrejs Vasiļjevs: Language Resources and Technology in Latvia (2010-2014)

16:40-17:05

Jurgita Vaičenonienė: How Relevant is the Distinction Between the Original and Translated Texts in General Corpora?

17:05-17:30

Posters‘ session and coffee

Ilze Auziņa, Mārcis Pinnis and Roberts Darģis: Comparison of Rule-based and Statistical Methods for Grapheme to Phoneme Modelling

Loïc Boizou and Francesco Zamblera: Syntactic engine for the Lithuanian Language

Ginta Garkāje, Evelīna Zilgalve and Roberts Darģis: Normalization and Automatised Sentiment Analysis of Contemporary Online Latvian Language

Gintare Grigonyte and Björn Hammarberg: Pronunciation and Spelling: The Case of Misspellings in Swedish L2 Written Essays

Aušra Mackutė-Varoneckienė and Tomas Krilavičius: Empirical Study on Unsupervised Feature Selection for Document Clustering

Vytautas Rudžionis, Gailius Raškinis, Kastytis Ratkevičius, Algimantas Rudžionis and Gintarė Bartišiūtė: Medical – pharmaceutical Information System with Lithuanian Voice Commands

Ottokar Tilk and Tanel Alumäe: Multi-Domain Recurrent Neural Network Language Model for Medical Speech Recognition

Alexander Tkachenko, Timo Petmanson and Sven Laur: Hybrid Lemmatizer for Estonian

17:30-18:00

Networking time (coffee, wine and snacks sponsored by Tilde)

18:00-18:30

Free time
18:30-19:30

Excursion [Kaunas City, gather in the lobby of the hotel]

Please register to the excursion in the online registration form.

19:30-21:00

Conference dinner [Restaurant 'Old Cellars' (Senieji Rūsiai) in town centre]

Please register to the dinner in the online registration form.

 

27 September (Saturday)

[Hotel/Alfa hall/2nd floor]

08:30-18:00

Registration desk open

09:00-09:45

KEYNOTE - Steven Krauwer:

What CLARIN can do for you and what you can do for CLARIN

 

Oral presentations: Speech Technology

Chair: Ilze Auziņa

09:45-10:10

Tanel Alumäe: Full-duplex Speech-to-text System for Estonian

10:10-10:35

Einar Meister, Rainer Metsvahi and Sascha Fagel: Evaluation of the Estonian Audiovisual Speech Synthesis

10:35-11:00

Coffee break

11:00-11:25

Meelis Mihkla, Indrek Hein, Indrek Kiissel, Artur Räpp, Risto Sirts and Tanel Valdna: A System of Spoken Subtitles for Estonian Television

11:25-11:50

Liisi Piits, Indrek Hein, Indrek Kiissel and Elgar Kudritski: Statistical Parametric Speech Synthesis for Online Dictionaries – Problems and Solutions

11:50-12:15

Tomas Rasymas and Vytautas Rudžionis: Combining Multiple Foreign Language Speech Recognizers by using Neural Networks

12:15-12:40

Inese Vira and Andrejs Vasiljevs: The Development of Conversational Agent Based Interface

12:40-13:45

Lunch [hotel/restaurant/2nd floor or city centre]

If you wish to have lunch in the hotel restaurant please mark the option in the online registration form. Alternatively you are welcome to have lunch in the city.

13:45-14:30

Poster session

Daiga Deksne and Inguna Skadiņa: Error-Annotated Corpus for Latvian

Kristiina Jokinen and Graham Wilcock: Automatic and Manual Annotations in First Encounter Dialogues

Laura Kamandulytė-Merfeldienė and Povilas Godliauskas: Creating and Working with Corpus of Spoken Lithuanian

Katarzyna Klessa and Nicole Nau: Compilation of Language Resources and On-line Dissemination of Knowledge about Endangered Languages and Linguistic Heritage

Alexandr N. Kornev, Ingrida Balčiūnienė, Margarita G. Selezneva and Anatolij A. Sorokin: How to Compute Reading Development Strategy? Evidence from Russian-Speaking Children

Neringa Krapikaitė: Using the ToBI Transcription to Analyze the Intonation of Lithuanian

Lya Meister and Einar Meister: Development of the Corpus of Estonian Adolescent Speech

Agnė Nugaraitė: A Translation-based, Automatically Derived Thesaurus of Lithuanian Adjectives

Siim Orasmaa: How Availability of Explicit Temporal Cues Affects Manual Temporal Relation Annotation

Askars Salimbajevs and Mārcis Pinnis: Towards Large Vocabulary Automatic Speech Recognition for Latvian

 

Oral presentations: Methods in Computational Linguistics (2)

Chair: Inguna Skadiņa   

14:30-14:55

Loïc Boizou, Jolanta Kovalevskaitė, Erika Rimkutė and Roger Wechsler: English-Lithuanian Word Alignment with Bilingwis: Evaluation of the Alignment

14:55-15:20

Valdis Girgždis, Maija Kāle, Mārtiņš Vaicekauskis, Ieva Zariņa and Inguna Skadiņa: Tracing Mistakes and Finding Gaps in Automatic Word Alignments for Latvian-English Translation

15:20-15:45

Jānis Peisenieks and Raivis Skadiņš: Uses of Machine Translation in the Sentiment Analysis of Tweets

15:45-16:10

Mārcis Pinnis: Bootstrapping of a Multilingual Transliteration Dictionary for European Languages

16:10-16:35

Raivis Skadiņš, Valters Šics and Roberts Rozis: Building the World's Best General Domain MT for Baltic Languages

16:35-16:45

Coffee break

16:45-17:15

Rūta Petrauskaitė: Quo vadis, HLT of the Baltic languages?

17:15-17:45

Panel Discussion [hotel/Alfa hall/2nd floor]

"Quo vadis, HLT of the Baltic languages?"

17:45-18:00

Closing of the Conference

 

 

Start

Review our website information for an overview of conference features.

 

Generate Ideas

Exchange information, find new synergies and promote initiatives for international cooperation.

 

Engage

Share your new ideas and recent advances in human language processing.

 

Promote

Promote cooperation between the research communities of computer science and linguistics.