CICLing 2009
Program (without first days)

 

Buses leaving in the morning

 Tuesday 

 Wednesday 

 Thursday 

 Friday 

 Saturday

8 am

7 am

8 am

8am

7 am

 

 

Overall program

Tuesday

Talks

Wednesday

Tour: Monarch butterfly wintering site, at 7 am

Thursday

Talks

Friday

Talks; closing ceremony; possibly banquet

Saturday

Tour: Xochicalco pyramids, Cacahuamilpa cave, town of Taxco, at 7 am

 

 

Program for the days of talks

Tuesday 3

 

Thursday 5

 

Friday 6

 

  

 

 

 

 

 

8:00 Bus from hotel

 

8:00 Bus from hotel

 

8:00 Bus from hotel

 

Keynote:
Jill Burstein

 

Keynote:
Ken Church

 

Keynote:
Dekang Lin

Technical session

 

Technical session

 

Technical session

Lunch

 

Lunch

 

Lunch

 

Technical session

 

Technical session

 

Technical session

Special event:
Jill Burstein

 

Special event:
Ken Church

 

Special event:
Dekang Lin

Bus to hotel

 

Bus to hotel

 

Closing ceremony

 

 

 

 

 

 

 

Bus to banquet* -
hotel - banquet*

 

 

Banquet*

 

* In case if the banquet is organized   

Bus to hotel*

 

                                                  

                       

 

 

page 

 

Tuesday

 

 

 

 

8:00

Bus to the conference venue (don’t be late!)

 

 

 

 

 

Trends and Opportunities I

 

 

 

 

09:00‑09:55

Keynote talk:
Opportunities for Natural Language Processing Research in Education

 6

 

Jill Burstein

 

 

 

 

10:00‑10:10

Break

 

 

 

 

 

Corpus Analysis and Lexical Resources I

 

 

 

 

10:15‑10:30

Evaluation of the Syntactic Annotation in EPEC, the Reference Corpus for the Processing of Basque

 72

 

Larraitz Uria, Ainara Estarrona, Izaskun Aldezabal, Maria Jesús Aranzabe, Arantza Díaz de Ilarraza, and Mikel Iruskieta

 

 

 

 

 

Information Retrieval and Text Comparison I

 

 

 

 

10:35‑10:50

Empirical Paraphrasing of Modern Greek Text in Two Phases: An Application to Steganography

535

 

Katia Lida Kermanidis and Emmanouil Magkos

 

 

 

 

 

Applications to the Humanities

 

 

 

 

10:55‑11:10

Linguistic Ethnography: Identifying Dominant Word Classes in Text

594

 

Rada Mihalcea and Stephen Pulman

 

11:15‑11:30

Break

 

 

 

 

 

Extraction of Lexical Knowledge

 

 

 

 

11:35‑11:50

Semantic Mapping for Related Term Identification

111

 

Rafael E. Banchs

 

11:55‑12:10

An Improved Automatic Term Recognition Method for Spanish

125

 

Alberto Barrón-Cedeño, Gerardo Sierra, Patrick Drouin, and Sophia Ananiadou

 

12:15‑12:30

Bootstrapping a Verb Lexicon for Biomedical Information Extraction

137

 

Giulia Venturi, Simonetta Montemagni, Simone Marchi, Yutaka Sasaki, Paul Thompson, John McNaught, and Sophia Ananiadou

 

12:35‑12:50

TermeX: A Tool for Collocation Extraction

149

 

Davor Delac, Zoran Krleza, Jan Snajder, Bojana Dalbelo Basic, and Frane Saric

 

12:55‑13:50

Lunch

 

 

 

 

 

Text Summarization II (cont.)

 

 

 

 

13:55‑14:10

The Decomposition of Human-Written Book Summaries

582

 

Hakan Ceylan and Rada Mihalcea

 

 

 

 

 

Morphology and Parsing I

 

 

 

 

14:15‑14:30

Guessers for Finite-State Transducer Lexicons

158

 

Krister Lindén

 

14:35‑14:50

Formal Grammar for Hispanic Named Entities Analysis

183

 

Grettel Barceló, Eduardo Cendejas, Grigori Sidorov, and Igor A. Bolshakov

 

14:55‑15:15

Break

 

 

 

 

14:20‑15:35

Automatic Extraction of Clause Relationships from a Treebank

195

 

Oldrich Kruza and Vladislav Kubon

 

15:40‑15:55

A General Method for Transforming Standard Parsers into Error-Repair Parsers

207

 

Carlos Gómez-Rodríguez, Miguel A. Alonso, and Manuel Vilares

 

 

 

 

 

Semantics

 

 

 

 

16:00‑16:15

Topic-Focus Articulation from the Semantic Point of View

220

 

Marie Duzí

 

16:20‑16:35

AORTE for Recognizing Textual Entailment

245

 

Reda Siblini and Leila Kosseim

 

 

 

 

16:40‑16:50

Break

 

 

 

 

16:55‑17:50

Special event: Jill Burstein

 

 

 

 

18:00

Bus to the hotel (don’t be late!)

 

 

 

 

 

Wednesday: Monarch butterfly site

 

 

 

 

7:00

Bus to the tour (don’t be late!); back to hotel about midnight

 

 

 

 

 

Thursday

 

 

 

 

8:00

Bus to the conference venue (don’t be late!)

 

 

 

 

 

Corpus Analysis and Lexical Resources II (cont.)

 

 

 

 

9:00‑9:55

Keynote talk:
Substring Statistics

 53

 

Kyoji Umemura and Kenneth Church

 

 

 

 

10:00‑10:10

Break

 

 

 

 

 

Word Sense Disambiguation

 

 

 

 

10:15‑10:30

Semi-supervised Word Sense Disambiguation Using the Web as Corpus

256

 

Rafael Guzmán-Cabrera, Paolo Rosso, Manuel Montes-y-Gómez, Luis Villaseñor-Pineda, and David Pinto-Avendaño

 

 

 

 

10:35‑10:50

Semi-supervised Clustering for Word Instances and its Effect on Word Sense Disambiguation

266

 

Kazunari Sugiyama and Manabu Okumura

 

10:55‑11:20

Invited Paper:
Alleviating the Problem of Wrong Coreferences in Web Person Search

280

 

Octavian Popescu and Bernardo Magnini

 

11:25‑11:50

Break

 

 

 

 

11:55‑12:10

Improved Unsupervised Name Discrimination with Very Wide Bigrams and Automatic Cluster Stopping

294

 

Ted Pedersen

 

 

 

 

 

Machine Translation and Multilinguism

 

 

 

 

12:15‑12:40

Best Student Paper Award:
Enriching Statistical Translation Models Using a Domain-Independent Multilingual Lexical Knowledge Base

306

 

Miguel García, Jesús Giménez, and Lluís Màrquez

 

12:45‑13:10

Best Paper Award, 1st place:
Cross-Language Frame Semantics Transfer in Bilingual Corpora

332

 

Roberto Basili, Diego De Cao, Danilo Croce, Bonaventura Coppola, and Alessandro Moschitti

 

 

 

 

13:15‑14:10

Lunch

 

 

 

 

14:15‑14:30

Exploiting Parallel Treebanks to Improve Phrase-Based Statistical Machine Translation.

318

 

John Tinsley, Mary Hearne, and Andy Way

 

14:35‑14:50

A Parallel Corpus Labeled Using Open and Restricted Domain Ontologies

346

 

Ester Boldrini, Sergio Ferrández, Ruben Izquierdo, David Tomás, and Jose Luis Vicedo

 

14:55‑15:10

Language Identification on the Web: Extending the Dictionary Method

357

 

Radim Rehurek and Milan Kolkus

 

 

 

 

15:15‑15:30

Break

 

 

 

 

 

Information Extraction and Text Mining I

 

 

 

 

15:35‑15:50

Business Specific Online Information Extraction from German Websites

369

 

Yeong Su Lee and Michaela Geierhos

 

15:55‑16:10

Low-Cost Supervision for Multiple-Source Attribute Extraction

382

 

Joseph Reisinger and Marius Pasca

 

16:15‑16:30

An Integrated Architecture for Processing Business Documents in Turkish

394

 

Serif Adali, A. Coskun Sonmez, and Mehmet Gokturk

 

16:35‑16:50

Using a Bigram Event Model to Predict Causal Potential

430

 

Brandon Beamer and Roxana Girju

 

16:55‑17:10

Semantic-Based Temporal Text-Rule Mining

442

 

Kjetil Nørvag and Ole Kristian Fivelstad

 

 

 

 

17:15‑17:20

Break

 

 

 

 

 

Trends and Opportunities II (cont.)

 

 

 

 

17:25‑18:20

Special event: Ken Church
Includes: Has Computational Linguistics Become More Applied?

 1

 

Kenneth Church

 

 

 

 

18:30

Bus to the hotel (don’t be late!)

 

 

 

 

 

Friday

 

 

 

 

8:00

Bus to the conference venue (don’t be late!)

 

 

 

 

09:00‑09:55

Keynote talk

 

 

Dekang Lin

 

 

 

 

10:00‑10:10

Break

 

 

 

 

 

Information Extraction and Text Mining II (cont.)

 

 

 

 

10:15‑10:40

Best Paper Award, 2nd place:
Detecting Protein-Protein Interactions in Biomedical Texts Using a Parser and Linguistic Resources

406

 

Gerold Schneider, Kaarel Kaljurand, and Fabio Rinaldi

 

10:45‑11:10

Best Paper Award, 3rd place:
Learning to Learn Biological Relations from a Small Training Set

418

 

Laura Alonso i Alemany and Santiago Bruno

 

11:15‑11:30

Generating Executable Scenarios from Natural Language

456

 

Michal Gordon and David Harel

 

11:35‑11:45

Break

 

 

 

 

11:50‑12:05

Determining the Polarity and Source of Opinions Expressed in Political Debates.

468

 

Alexandra Balahur, Zornitsa Kozareva, and Andrés Montoyo

 

 

 

 

 

Information Retrieval and Text Comparison II (cont.)

 

 

 

 

12:10‑12:25

Query Translation and Expansion for Searching Normal and OCR-Degraded Arabic Text

481

 

Tarek Elghazaly and Aly Fahmy

 

12:30‑12:45

NLP for Shallow Question Answering of Legal Documents Using Graphs

498

 

Alfredo Monroy, Hiram Calvo, and Alexander Gelbukh

 

 

 

 

12:50‑13:45

Break

 

 

 

 

13:50‑14:05

Semantic Clustering for a Functional Text Classi.cation Task

509

 

Thomas Lippincott and Rebecca Passonneau

 

14:10‑14:25

Reducing the Plagiarism Detection Search Space on the Basis of the Kullback-Leibler Distance

523

 

Alberto Barrón-Cedeño, Paolo Rosso, and José-Miguel Benedí

 

14:30‑14:45

BorderFlow: A Local Graph Clustering Algorithm for Natural Language Processing

547

 

Axel-Cyrille Ngonga Ngomo and Frank Schumacher

 

14:50‑15:05

Generalized Mongue-Elkan Method for Approximate Text String Comparison

559

 

Sergio Jimenez, Claudia Becerra, Alexander Gelbukh, and Fabio Gonzalez

 

 

 

 

15:10‑15:25

Break

 

 

 

 

 

Text Summarization II (cont.)

 

 

 

 

15:30‑15:45

Estimating Risk of Picking a Sentence for Document Summarization

571

 

Chandan Kumar, Prasad Pingali, and Vasudeva Varma

 

 

 

 

 

Morphology and Parsing II (cont.)

 

 

 

 

15:50‑16:15

Invited Paper:
Combining Language Modeling and Discriminative Classification for Word Segmentation

170

 

Dekang Lin

 

 

 

 

 

Corpus Analysis and Lexical Resources III (cont.)

 

 

 

 

16:20‑16:35

Reducing Noise in Labels and Features for a Real World Dataset: Application of NLP Corpus Annotation Methods.

86

 

Rebecca J. Passonneau, Cynthia Rudin, Axinia Radeva, and Zhi An Liu

 

16:40‑16:55

Unsupervised Classification of Verb Noun Multi-Word Expression Tokens

 98

 

Mona T. Diab and Madhav Krishna

 

 

 

 

17:00‑17:10

Break

 

 

 

 

17:15‑18:10

Special event: Dekang Lin

 

 

 

 

18:20

Bus to the hotel (don’t be late!)

 

 

 

 

 

Saturday: Xochicalco & Cave

 

 

 

 

7:00

Bus to the tour (don’t be late!); back to hotel about midnight