You can download program in PDF format here.

11 May 2011

Registration 8.00–17.30

NODALIDA Satellite events

Satellite Workshops

  • Workshop on Creation, Harmonization and Application of Terminology Resources (Museum Hall)
  • Workshop on Constraint Grammar Applications (Room 205)
  • Workshop on visibility and availability of LT resources (Auditorium 16)

19:00 — Welcome reception (Albert Hotel, Dzirnavu iela 33)

12 May 2011

Registration 8.00–11.00

9.00–9.30 Opening
Mārcis Auziņš (Rector of the University of Latvia)
Janne Bondi Johannessen (President of NEALT)
Inguna Skadiņa (Chair of the local Organizing Committee)
Bolette Sandford Pedersen (Chair of the Program Committee)
Small Hall
9.30–10.30 Invited Talk
Chair: Costanza Navarretta
Topic: Discourse Structures and Language Technologies [slides]
Prof. Bonnie Webber (University of Edinburgh)
Small Hall
10.30–11.00CoffeeRoom 240
11.00–13.003 parallel sessions: REGULAR papers
Corpus creation, annotation and use (Chair: Eiríkur Rögnvaldsson)Auditorium 16
11.00–11.30Creating Comparable Multimodal Corpora for Nordic Languages
Costanza Navarretta, Elisabeth Ahlsén, Jens Allwood, Kristiina Jokinen and Patrizia Paggio
11.30–12.00Iterative, MT-based Sentence Alignment of Parallel Texts
Rico Sennrich and Martin Volk
12.00–12.30Evaluation of terminologies acquired from comparable corpora: an application perspective
Estelle Delpech
12.30–13.00What kind of corpus is a web corpus?
Janne Bondi Johannessen and Emiliano Raúl Guevara
Text and language classification (Chair: Hanne Fersøe)Museum Hall
11.00–11.30Estimating language relationships from a parallel corpus. A study of the Europarl corpus
Taraka Rama and Lars Borin
11.30–12.00Improving Sentence-level Subjectivity Classification through Readability Measurement
Robert Remus
12.00–12.30Convolution Kernels for Subjectivity Detection
Michael Wiegand and Dietrich Klakow
Morphology and POS tagging (Chair: Anders Nøklestad)Room 205
11.00–11.30Combining Statistical Models for POS Tagging using Finite-State Calculus
Miikka Silfverberg and Krister Lindén
11.30–12.00Decision Strategies for Incremental POS Tagging
Niels Beuck, Arne Köhn and Wolfgang Menzel
12.00–12.30Explorations on Positionwise Flag Diacritics in Finite-State Morphology
Anssi Yli-Jyrä
12.30–13.00Morphological analysis of a non-standard language variety
Heiki-Jaan Kaalep and Kadri Muischnek
14.00–15.3012 Posters and Demos (Chair: Janne Bondi Johannessen)
Wordnets and lexical issuesMuseum Hall
 Do wordnets also improve human performance on NLP tasks?
Kristiina Muhonen and Krister Lindén
 The Formal Patterns of the Lithuanian Verb Forms
Loïc Boizou
 Identification of sense selection in regular polysemy using shallow features
Hector Martinez Alonso, Núria Bel and Bolette Sandford Pedersen
 "Andre ord" — a wordnet browser for the Danish wordnet, DanNet (DEMO)
Anders Johannsen and Bolette Sandford Pedersen
SyntaxMuseum Hall
 Extraction from relative and embedded interrogative clauses in Danish
Anne Bjerre
 Something Old, Something New — Applying a Pre-trained Parsing Model to Clinical Swedish
Martin Hassel, Aron Henriksson and Sumithra Velupillai.
 A double-blind experiment on interannotator agreement: the case of dependency syntax and Finnish
Atro Voutilainen and Tanja Purtonen
 A Prague Markup Language profile for the SemTi-Kamols grammar model
Lauma Pretkalniņa, Gunta Nešpore, Kristīne Levāne-Petrova and Baiba Saulīte
 CFG based grammar checker for Latvian
Daiga Deksne and Raivis Skadins
 Evaluating the effect of word frequencies in a probabilistic generative model of morphology
Sami Virpioja, Oskar Kohonen and Krista Lagus
 Modularisation of Finnish Finite-State Language Description — Towards Wide Collaboration in Open Source Development of a Morphological Analyser
Tommi Pirinen
Machine translationMuseum Hall
 Iterative reordering and word alignment for statistical MT
Sara Stymne
15.30–15.45CoffeeRoom 240
15.45–17.153 parallel sessions: REGULAR papers
Speech (Chair: Meelis Mihkla)Auditorium 16
15.45–16.15Corrective re-synthesis of deviant speech using unit selection
Sofia Strömbergsson
16.15–16.45Fishing in a speech stream, angling for a lexicon
Peter Juel Henrichsen
16.45–17.15Psycho-acoustically motivated formant feature extraction
Bea Valkenier, Dirkjan Krijnders, Ronald Van Elburg and Tjeerd Andringa
Search and information extraction (Chair: Costanza Navarretta)Museum Hall
15.45–16.15Semantic search in literature as an e-Humanities research tool: CONPLISIT — Consumption patterns and life-style in 19th century Swedish literature
Lars Borin, Markus Forsberg and Christer Ahlberger
16.15–16.45Relevance Prediction in Information Extraction using Discourse and Lexical Features
Silja Huttunen, Arto Vihavainen and Roman Yangarber
16.45–17.15Experiments on Lithuanian Term Extraction
Gintarė Grigonytė, Erika Rimkutė, Andrius Utka and Loïc Boizou
Syntax, indexing (Chair: Jussi Karlgren)Room 205
15.45–16.15Editing Syntax Trees on the Surface
Peter Ljunglöf
16.15–16.45Using graphical models for PP attachment
Anders Søgaard
16.45–17.15Random Indexing Re-Hashed
Erik Velldal
17.15–18.15 Invited Talk
Chair: Inguna Skadiņa
Topic: When FrameNet meets a Controlled Natural Language [slides]
Prof. Guntis Bārzdiņš (University of Latvia)
Small Hall
19.30–Conference dinnerRestaurant Rozengrāls
Rozena iela 1

13 May 2011

9.00–10.00 Invited Talk
Chair: Kristiina Jokinen
Topic: Bare-Bones Dependency Parsing — A Case for Occam's Razor? [slides]
Prof. Joakim Nivre (Uppsala University)
Small Hall
10.00–10.30CoffeeRoom 240
10.30–12.003 parallel sessions: REGULAR papers and STUDENT papers
Lexicon, etymology (Chair: Bolette Sandford Pedersen)Auditorium 16
10.30–11.00A FrameNet for Danish
Eckhard Bick
11.00–11.30The Impact of Part-of-Speech Filtering on Generation of a Swedish-Japanese Dictionary Using English as Pivot Language
Ingemar Hjälmstad, Martin Hassel and Maria Skeppstedt
11.30–12.00Probabilistic Models for Alignment of Etymological Data
Hannes Wettig and Roman Yangarber
Machine translation; classification (Chair: Andrejs Vasiļjevs)Museum Hall
10.30–11.00Disambiguation of English Contractions for Machine Translation of TV Subtitles
Martin Volk and Rico Sennrich
11.00–11.30Toponym Disambiguation in English-Lithuanian SMT System with Spatial Knowledge
Raivis Skadiņš, Tatiana Gornostay and Valters Šics
11.30–12.00A quantitative and qualitative analysis of Nordic surnames
Eirini Florou and Stasinos Konstantopoulos
Student papers (Chair: Normunds Grūzītis)Room 205
10.30–11.00Evaluating the speech quality of the Norwegian synthetic voice Brage
Marius Olaussen
11.00–11.30A Statistical Part-of-Speech Tagger for Persian
Mojgan Seraji
11.30–12.00Linguistic Motivation in Automatic Sentence Alignment of Parallel Corpora: the Case of Danish-Bulgarian and English-Bulgarian
Angel Genov and Georgi Iliev
13.00–14.3012 Posters and Demos (Chair: Kristiina Jokinen)
Classification & summarizationMuseum Hall
Automatic summarization as means of simplifying texts, an evaluation for Swedish
Christian Smith and Arne Jönsson
Experiments to investigate the utility of nearest neighbour metrics based on linguistically informed features for detecting textual plagiarism
Per Almquist and Jussi Karlgren
A categorization scheme for analyzing rules from a handbook of Swedish writing rules
Jody Foo
Dialect classification in the Himalayas: a computational approach
Anju Saxena and Lars Borin
Knowledge systemsMuseum Hall
Query Constraining Aspects of Knowledge
Ann-Marie Eklund
Automatic Question Generation from Swedish Documents as a Tool for Information Extraction
Kenneth Wilhelmsson
Corpus creation, annotation and useMuseum Hall
Knowledge-free Verb Detection through Sentence Sequence Alignment
Christian Hänig
A Gold Standard for English–Swedish Word Alignment
Maria Holmqvist and Lars Ahrenberg
Corpus-based terminology: detection, description and representation of knowledge-rich contexts in Russian
Anne-Kathrin Schumann
Student postersMuseum Hall
Identification of context markers for Russian nouns
Anastasia Shimorina and Maria Grachkova
Finding statistically motivated features influencing subtree alignment performance
Gideon Kotzé
14.30–15.30NEALT Business meetingSmall Hall
15.30–16.00Closing Small Hall
16.00–16.30Coffee Museum Hall