Programme CLIN 19
Thursday 22 January 2009, Academiegebouw, Broerstraat 5, Groningen, The Netherlands, +31 50 363 5250 (pdf of programme).
Room Offerhauszaal | Room Geertsemazaal | Room A900 | Room A901 | Room A12 | |
08:30 09:30 | Registration and coffee (Room Bruinszaal) | ||||
09:30 09:50 |
Language models for contextual error detection and correction
Stehouwer and Van Zaanen |
An Aspect Based Document Representation for Event Detection
De Smet and Moens |
A treebank-driven investigation of predicate complements in Dutch
Van Eynde |
Solving analogies between symbols strings, with or without constraints
Manguin |
Towards Acquisition of Taxonomic Inference
Lendvai |
09:55 10:15 |
In Search of the Why: What have we learnt?
Verberne, Boves, et al. |
Using the transitivity of meaning for distributional methods to remedy data sparseness
Van der Plas |
Extracting a deep German HPSG grammar from a detailed dependency treebank
Cramer and Zhang |
Phrase Translation Probabilities Estimation Using Latent Segmentations and Smoothed Expectation-Maximization
Mylonakis and Sima'an |
A Tagger-Lemmatiser for 14th Century Dutch Charters
Van Halteren and Rem |
10:20 10:40 |
Klinkende Taal: an automatic system for readability testing
Koornwinder |
Using lexico-syntactic patterns for automatic antonym extraction
Lobanova, Spenader and Van der Kleij |
Automated Methods for Extending the Lexicons of Deep Grammars
Cholakov |
Evaluation of pairwise string alignment methods
Wieling, Prokic and Nerbonne |
A comparison of HMM and Maximum Entropy models for Sequential Tagging
Zhao |
10:45 11:05 |
Linking Wikipedia Categories to Dutch WordNet
Bouma |
Extending a Shallow Parser with PP-attachment and a comparison with full statistical parsing
Van Asch and Daelemans |
Getting (un)expected asymmetries in parsing head-final languages
Chesi |
Multiple sequence alignments in linguistics
Prokic, Wieling and Nerbonne |
|
11:05 11:30 | Coffee (Room Bruinszaal) | ||||
11:30 12:30 | Invited talk by Mirella Lapata
(University of Edinburgh) in Room Offerhauszaal:
Constraint-based Sentence Compression: An Integer Programming Approach | ||||
12:30 13:30 | Lunch (Rooms Bruinszaal and Spiegelzaal) | ||||
13:30 13:50 |
Language-independent bilingual terminology extraction from a multilingual parallel corpus
Lefever, Macken and Hoste |
A practical and extensible algorithm for frequent structure discovery in large corpora
Martens |
Extracting domain ontologies from social media applications
Monachesi and Mossel |
Semi-supervised adaptation of a Syntactic Disambiguation Model using Structural Correspondence Learning
Plank and Van Noord |
Unsupervised Morphology Learning Using a Lexicalized Grammar
Coltekin |
13:55 14:15 |
Aligning complex translational correspondences via bootstrapping
Macken and Daelemans |
Dutch from logic
Cremers and Hijzelendoorn |
Generating a Non-English Subjectivity Lexicon: Relations That Matter
Jijkoun and Hofmann |
Unsupervised Frame Induction with Non-negative Matrix Factorization
Van de Cruys |
Training a parser on artificially fragmented data for spoken language understanding
Van der Plas, Henderson and Merlo |
14:20 14:40 |
Automatic filtering of parallel corpora for improving alignment accuracy
Kotzé |
Constructing a Domain Ontology from a Domain Database and the Web
Van Erp |
Modelling Lexical Variation with Word Space Models
Peirsman and Geeraerts |
Predicate-argument Frequencies in Dutch Pronoun Resolution
Bouma and Bouma |
Unsupervised Methods for Head Assignment
Sangati |
14:45 15:05 |
Translating Questions for Cross-lingual QA
Tiedemann |
Bootstrapping Approach for Learning Part-Whole Relations
Ittoo and Bouma |
Clustering Headlines for Automatic Paraphrase Acquisition
Wubben, Van den Bosch, et al. |
A Semantic Approach to Antecedent Selection in Verb Phrase Ellipsis
De Vries |
Impact of lexical probabilities on adapting a PCFG to a new domain.
Deoskar |
15:05 16:00 | Poster session (Economiehal) and coffee (Room Bruinszaal) | ||||
16:00 16:20 |
Aligning syntactic divergences through parse tree transformation
Vanallemeersch |
Automatically extending linguistically enriched data
Theijssen, Oostdijk and Van Halteren |
Enhancing Coverage of Multilingual Lexicalised Grammars
Zhang, Kordoni and Cholakov |
Definition extraction using a sequential combination of grammars and machine learning classifiers
Westerhout and Monachesi |
Annotation of Temporal Information in French Texts
Bittar |
16:25 16:45 |
Automatic Text Categorization: Adding Syntactic Knowledge
Ruette |
Harvesting Accurate and Fast Confusible Detectors
Van den Bosch |
PhraseNET: a proposal to identify and to extract phraseological units from electronic texts
De Lucca (no show) |
TEI-conformant XML encoding scheme for corpora with multiple levels of annotation
Banski, Bemowski and Przepiórkowski |
Elephants and Optimality Again. SA-OT accounts for pronoun resolution in child language.
Biró |
16:50 17:10 |
Bootstrapping Automatic Synonymy Extraction
Heylen, Peirsman and Geeraerts |
A generalized method for iterative error mining in parsing results
De Kok and Van Noord |
Corpus-based Source Language Modeling Using Parallel Treebanks
Van den Bogaert |
Applying the LD to Catalan dialects: a brief comparison of two dialectometric approaches
Valls and Nerbonne |
Vagueness and Interaction: Notes on a Project
Fernandez |
17:15 17:35 |
Syntactic-Semantic Treebank for Domain Ontology Creation
Osenova and Simov |
Identification of bilingual named-entities from Wikipedia using a pair Hidden Markov Model
Nabende |
Corpus-based Target Language Modeling Using Treebanks
Vandeghinste |
Language technology and semantic knowledge in eLearning
Monachesi |
A Regression Model for the English Benefactive Alternation
Theijssen, Van Halteren, et al. |
17:35 19:00 | Drinks (Room Bruinszaal) |