Computational Linguistics and Intelligent Text Processing

Language Resources

A Distributed Database System for Developing Ontological and Lexical

Resources in Harmony    . . 1

Aleˇs Hor´ak, Piek Vossen, and Adam Rambousek

Verb Class Discovery from Rich SyntacTIc Data  . . . . 16

Lin Sun, Anna Korhonen and Yuval Krymolowski

Growing TreeLex     28

Anna Kup´s´c and Anne Abeill´e

AcquisiTIon of Elementary Synonym RelaTIons from Biological

Structured Terminology    . 40

Thierry Hamon and Natalia Grabar

A Comparison of Co-occurrence and Similarity Measures as SimulaTIons

of Context     52

Stefan Bordag

Various Criteria of Collocation Cohesion in Internet: Comparison of

Resolving Power     . 64

Igor A. Bolshakov, Elena I. Bolshakova, Alexey P. Kotlyarov, and

Alexander Gelbukh

Why Don’t Romanians Have a Five O’clock Tea, Nor Halloween, But

Have a Kind of Valentines Day?   . . . . . 73

Corina For˘ascu

Best Student Paper Award

SIGNUM: A Graph Algorithm for Terminology Extraction  85

Axel-Cyrille Ngonga Ngomo

Morphology and Syntax

Arabic Morphology Parsing Revisited   . 96

Suhel Jaber and Rodolfo Delmonte

A Probabilistic Model for Guessing Base Forms of New Words by

Analogy     . . 106

Krister Lind´en

XIV Table of Contents

Unsupervised and Knowledge-Free Learning of Compound Splits and

Periphrases     . . . . . 117

Florian Holz and Chris Biemann

German Decompounding in a Difficult Corpus  . . . . . 128

Enrique Alfonseca, Slaven Bilac, and Stefan Pharies

Clause Boundary Identification Using Conditional Random Fields 140

R. Vijay Sundar Ram and Sobha Lalitha Devi

Semantics and Discourse

Invited Paper

Natural Language as the Basis for Meaning Representation and

Inference     . . 151

Ido Dagan, Roy Bar-Haim, Idan Szpektor, Iddo Greental, and

Eyal Shnarch

Layer Structures and Conceptual Hierarchies in Semantic

Representations for NLP    171

Hermann Helbig, Ingo Gl¨ockner, and Rainer Osswald

Deep Lexical Semantics    . 183

Jerry R. Hobbs

On Ontology Based Abduction for Text Interpretation  . . . 194

Irma Sofia Espinosa Peraldi, Atila Kaya, Sylvia Melzer, and

Ralf M¨oller

Analysis of Joint Inference Strategies for the Semantic Role Labeling of

Spanish and Catalan    . . . 206

Mihai Surdeanu, Roser Morante, and Llu´ıs M`arquez

A Preliminary Study on the Robustness and Generalization of Role

Sets for Semantic Role Labeling   . . . . . 219

Be˜nat Zapirain, Eneko Agirre, and Llu´ıs M`arquez

XTM: A Robust Temporal Text Processor   . . 231

Caroline Hag`ege and Xavier Tannier

Invited Paper

What We Are Talking about and What We Are Saying about It . 241

Eva Hajiˇcov´a

Trusting Politicians’ Words (for Persuasive NLP)  . . 263

Marco Guerini, Carlo Strapparava, and Oliviero Stock

Table of Contents XV

Sense Annotation in the Penn Discourse Treebank  . 275

Eleni Miltsakaki, Livio Robaldo, Alan Lee, and Aravind Joshi

Word Sense Disambiguation and Named Entity

Recognition

A Semantics-Enhanced Language Model for Unsupervised Word Sense

Disambiguation     . . 287

Shou-de Lin and Karin Verspoor

Best Paper Award, 1st Place

Discovering Word Senses from Text Using Random Indexing . . . . 299

Niladri Chatterjee and Shiwali Mohan

Domain Information for Fine-Grained Person Name Categorization . . . . . 311

Zornitsa Kozareva, Sonia Vazquez, and Andres Montoyo

Language Independent First and Last Name Identification in Person

Names     . . . . 322

Octavian Popescu and Bernardo Magnini

Mixing Statistical and Symbolic Approaches for Chemical Names

Recognition     . . . . . 334

Florian Boudin, Juan Manuel Torres-Moreno, and Marc El-B`eze

Anaphora and Co-reference

Portuguese Pronoun Resolution: Resources and Evaluation  344

Ramon R´e Moya Cuevas, Willian Yukio Honda,

Diego Jesus de Lucena, Ivandr´e Paraboni, and

Patr´ıcia Rufino Oliveira

Semantic and Syntactic Features for Dutch Coreference Resolution . . . . . 351

Iris Hendrickx, Veronique Hoste, and Walter Daelemans

Machine Translation and Parallel Corpora

Invited Paper

Stat-XFER: A General Search-Based Syntax-Driven Framework for

Machine Translation   . . . . 362

Alon Lavie

XVI Table of Contents

Invited Paper

Statistical Machine Translation into a Morphologically Complex

Language     . 376

Kemal Oflazer

Translation Paraphrases in Phrase-Based Machine Translation . . . 388

Francisco Guzm´an and Leonardo Garrido

n-Best Reranking for the Efficient Integration of Word Sense

Disambiguation and Statistical Machine Translation  399

Lucia Specia, Baskaran Sankaran, and

Maria das Gra¸cas Volpe Nunes

Learning Finite State Transducers Using Bilingual Phrases  411

Jorge Gonz´alez, Germ´an Sanchis, and Francisco Casacuberta

Learning Spanish-Galician Translation Equivalents Using a Comparable

Corpus and a Bilingual Dictionary   . . . 423

Pablo Gamallo Otero and Jos´e Ramom Pichel Campos

Context-Based Sentence Alignment in Parallel Corpora  . . 434

Ergun Bi¸cici

Bilingual Segmentation for Alignment and Translation  . . . . 445

Chung-Chi Huang, Wei-Teh Chen, and Jason S. Chang

Dynamic Translation Memory: Using Statistical Machine Translation

to Improve Translation Memory Fuzzy Matches  . . . . 454

Ergun Bi¸cici and Marc Dymetman

Identification of Transliterated Foreign Words in Hebrew Script . . 466

Yoav Goldberg and Michael Elhadad

Natural Language Generation

Innovative Approach for Engineering NLG Systems: The Content

Determination Case Study    . . . . 478

Marco Fonseca, Leonardo Junior, Alexandre Melo, and

Hendrik Macedo

Speech Recognition

Comparison of Different Modeling Units for Language Model

Adaptation for Inflected Languages  . . . 488

Tanel Alum¨ae

Table of Contents XVII

Information Retrieval and Question Answering

Word Distribution Analysis for Relevance Ranking and Query

Expansion     500

Patricio Galeas and Bernd Freisleben

Hybrid Method for Personalized Search in Scientific Digital Libraries . . . 512

Thanh-Trung Van and Michel Beigbeder

Alignment-Based Expansion of Textual Database Fields . . . 522

Piroska Lendvai

Detecting Expected Answer Relations through Textual Entailment . . . . . 532

Matteo Negri, Milen Kouylekov, and Bernardo Magnini

Improving Question Answering by Combining Multiple Systems Via

Answer Validation    . . . . . 544

Alberto T´ellez-Valero, Manuel Montes-y-G´omez,

Luis Villase˜nor-Pineda, and Anselmo Pe˜nas

Text Classification

Evaluation of Internal Validity Measures in Short-Text Corpora . . 555

Diego Ingaramo, David Pinto, Paolo Rosso, and Marcelo Errecalde

Text Summarization

Arabic/English Multi-document Summarization with CLASSY—The

Past and the Future    . . . . 568

Judith D. Schlesinger, Dianne P. O’Leary, and John M. Conroy

Best Paper Award, 3rd Place

Lexical Cohesion Based Topic Modeling for Summarization  582

Gonenc Ercan and Ilyas Cicekli

Terms Derived from Frequent Sequences for Extractive Text

Summarization     . . 593

Yulia Ledeneva, Alexander Gelbukh, and

Ren´e Arnulfo Garc´ıa-Hern´andez

Spell Checking and Authoring Aid

Real-Word Spelling Correction with Trigrams: A Reconsideration of

the Mays, Damerau, and Mercer Model   . . . . . 605

Amber Wilcox-O’Hearn, Graeme Hirst, and Alexander Budanitsky

XVIII Table of Contents

Best Paper Award, 2nd Place

Non-interactive OCR Post-correction for Giga-Scale Digitization

Projects     . . 617

Martin Reynaert

Linguistic Support for Revising and Editing   . 631

Cerstin Mahlow and Michael Piotrowski

The Role of PP Attachment in Preposition Generation  . . . 643

John Lee and Ola Knutsson

EFL Learner Reading Time Model for Evaluating Reading

Proficiency     655

Katsunori Kotani, Takehiko Yoshimi, Takeshi Kutsumi,

Ichiko Sata, and Hitoshi Isahara

Author Index     . . 665