Recently added

DSpace/Manakin Repository

LOTOS: Recent submissions

  • Computational Linguistics in the Netherlands 2010 : Selected papers from the twentieth CLIN meeting (CLIN 2010) 
    Westerhout, Eline; Markus, Thomas; Monachesi, Paola (LOT, Netherlands Graduate School of Linguistics, 2010-11)
    This book contains a selection of papers presented at the twentieth meeting of Computational Linguistics in the Netherlands (CLIN). The meeting was organized by the UiL-OTS institute, which is part of Utrecht University ...
  • Paraphrasing Headlines by Machine Translation : Sentential paraphrase acquisition and generation using Google News 
    Wubben, Sander; Bosch, Antal van den; Krahmer, Emiel (LOT, Netherlands Graduate School of Linguistics, 2010-11)
    In this paper we investigate the automatic collection, generation and evaluation of sentential paraphrases. Valuable sources of paraphrases are news article headlines; they tend to describe the same event in various ...
  • To ish or not to ish? 
    Theijssen, Daphne; Halteren, Hans van; Boonpiyapat, Tip; Lohfink, Anna; Ruiter, Bas; Westerbeek, Hans (LOT, Netherlands Graduate School of Linguistics, 2010-11)
    In English, new adjectives can be coined by adding the suffix -ish. For instance, one can describe someone who acts like Arnold Schwarzenegger as Schwarzeneggerish. This paper investigates how the use of -ish is influenced ...
  • Dutch Dependency Parser Performance Across Domains 
    Plank, Barbara; Noord, Gertjan van (LOT, Netherlands Graduate School of Linguistics, 2010-11)
    In the past decade several natural language parsing systems have emerged, which use different methods and formalisms. For instance, systems that employ a hand-crafted grammar with a statistical disambiguation component ...
  • Emotion Classification in a Serious Game for Training Communication Skills 
    Vaassen, Frederik; Daelemans, Walter (LOT, Netherlands Graduate School of Linguistics, 2010-11)
    We describe the natural language processing component of a new serious gaming project, deLearyous, which aims at developing an environment in which users can improve their communication skills by interacting with a virtual ...
  • Comparison of applying Pair HMMs and DBN models in Transliteration Identification 
    Nabende, Peter (LOT, Netherlands Graduate School of Linguistics, 2010-11)
    Transliteration is aimed at dealing with unknown words in Cross Language Information Retrieval (CLIR) and Machine Translation (MT). Most of the transliteration tasks depend on a similarity estimation stage where a model ...
  • A Sentence Generator for Dutch 
    Kok, Daniël de; Noord, Gertjan van (LOT, Netherlands Graduate School of Linguistics, 2010-11)
    The paper presents an efficient, wide-coverage, sentence generator for Dutch, which employs the Alpino grammar and lexicon. This generator consists of a chart-based sentence realizer that builds grammatical sentences for ...
  • Extraction of Biomedical Events 
    Morante, Roser; Van Asch, Vincent; Daelemans, Walter (LOT, Netherlands Graduate School of Linguistics, 2010-11)
    In this paper we describe a memory-based machine learning system that extracts biomedical events from texts relying on information from contextual and syntactic features. The main characteristics of the system are that ...
  • Extending Memory-Based Machine Translation to Phrases 
    Gompel, Maarten van; Bosch, Antal van den; Berck, Peter (LOT, Netherlands Graduate School of Linguistics, 2010-11)
    We present a phrase-based extension to memory-based machine translation. This form of example-based machine translation employs lazy-learning classifiers to translate fragments of the source sentence to fragments of the ...
  • Finding Constraints for Semantic Relations via Clustering 
    Katrenko, Sophia; Adriaans, Pieter (LOT, Netherlands Graduate School of Linguistics, 2010-11)
    Automatic recognition of semantic relations constitutes an important part of information extraction. Many existing information extraction systems rely on syntactic information found in a sentence to accomplish this task. ...
  • Dutch Named Entity Recognition using Classifier Ensembles 
    Desmet, Bart; Hoste, Véronique (LOT, Netherlands Graduate School of Linguistics, 2010-11)
    This paper explores the use of classifier ensembles for the task of named entity recognition (NER) on a Dutch dataset. Classifiers from 3 classification frameworks, namely memory-based learning (MBL), conditional random ...
  • 30 years of the Dutch Language Union 
    Bosch, Linde van den (LOT, Netherlands Graduate School of Linguistics, 2010-11)
    "It is a great honour for me to address an audience of such renowned computational linguists. I would like to thank the organising committee of CLIN 2010 for this opportunity. The CLIN conference is held every year at a ...
  • Improving Successor Variety for Morphological Segmentation 
    Çöltekin, Çağrı (LOT, Netherlands Graduate School of Linguistics, 2010-11)
    Successor variety is a commonly used measure for segmentation in language processing. It is based on a simple idea that a large variety of letters (or phonemes) following an initial word (or utterance) segment indicates ...
  • Computational Linguistics in the Netherlands 2009 : Selected papers from the nineteenth CLIN meeting (CLIN 2009) 
    Plank, Barbara; Tjong Kim Sang, Erik; Van de Cruys, Tim (LOT, Netherlands Graduate School of Linguistics, 2009-12)
    This book contains a selection of papers presented at the nineteenth meeting of Computational Linguistics in the Netherlands (CLIN). The meeting took place at the University of Groningen in the Netherlands on 22 January ...
  • Invited talk: Social attention in the age of the web 
    Huberman, Bernardo (LOT, Netherlands Graduate School of Linguistics, 2010-11)
    The past decade has witnessed a momentous transformation in the way people interact, create and exchange information. Content is now coactively produced, shared, classified, and rated on the Web by millions of people, ...
  • A regression model for the English benefactive alternation : An efficient, practical, actually usable approach 
    Theijssen, Daphne; Halteren, Hans van; Fikkers, Karin; Groothoff, Frederike; Hoof, Lian van; Sande, Eva van de; Tiems, Jorieke; Verhagen, Véronique; Zande, Patrick van der (LOT, Netherlands Graduate School of Linguistics, 2009-12)
    In this paper, we use logistic regression modelling to predict the English benefactive alternation (He baked me a cake vs. He baked a cake for me). We developed a data set consisting of 107 instances in adult writing and ...
  • A treebank-driven investigation of predicative complements in Dutch : An efficient, practical, actually usable approach 
    Van Eynde, Frank (LOT, Netherlands Graduate School of Linguistics, 2009-12)
    Treebanks are used for various purposes in language technology, but the wealth of data they contain can also be put to good use for the purpose of linguistic description and linguistic theory. To demonstrate this I will ...
  • Frequent Structure Discovery in Treebanks : An efficient, practical, actually usable approach 
    Martens, Scott (LOT, Netherlands Graduate School of Linguistics, 2009-12)
    Discovering frequent structures within large natural language corpora is one of the core problems of corpus linguistics, but it is difficult to do for richly structured data. This paper describes a practical algorithm ...
  • Semantic Selectional Restrictions for Disambiguating Meronymy Relations : A non-representational DRT-like discourse semantics 
    Ittoo, Ashwin; Bouma, Gosse (LOT, Netherlands Graduate School of Linguistics, 2009-12)
    We present an unsupervised approach to automatically learn lexico-syntactic patterns encoding meronymy relations from texts. Our major contribution lies in alleviating the challenge of disambiguating polysemous patterns ...
  • Coreference without Discourse Referents : A non-representational DRT-like discourse semantics 
    Giorgolo, Gianluca; Unger, Christina (LOT, Netherlands Graduate School of Linguistics, 2009-12)
    We propose a non-representational, compositional treatment of anaphora. By nonrepresentational we mean working directly with denotations without relying on specific features of a representational language, such as discourse ...