CICLing-2005 program

CICLing-2005
New: Newly Corrected Final Program

Please let us know if there is any problem

See below the list of poster presentations and canceled talks

Only the abstract of each paper is available here. The full paper can be purchased from Springer-Verlag.

NEW: Recent Changes (Feb 12):

Moved: from Friday to Monday: Language Documentation: the Nahuatl Grammar. Mike Maxwell, Jonathan D. Amith. 464.

Moved: from Monday to Friday: A Modular Account of Information Structure in Extensible Dependency Grammar. Ralph Debusmann, Oana Postolache, and Maarika Traat. 26.

NEW: Recent Changes (Feb 11):

Cancelled: two talks on Thursday (by Xiaoguang Li).

Moved: to Thursday: Putting Pieces Together: Combining FrameNet, VerbNet and WordNet for Robust Semantic Parsing. Lei Shi and Rada Mihalcea. 99.

Changed: Thursday and Friday schedule after 16:55.

Note (Feb 10):

The time of the bus is in the format "Departure--Arrival," i.e., "08:10–08:50 Bus from hotel" means that the bus goes from the hotel exactly at 08:10 and arrives to the conf place approximately at 08:50. Don't be late: there will be no transportation after the bus has gone (well, see here).

Changes (Feb 8):

Added: A Modular Account of Information Structure in Extensible Dependency Grammar. Ralph Debusmann, Oana Postolache, and Maarika Traat. 26.

(wait... loading...)

Time	Title	Author	Page

Sunday Cultural program

09:00–19:30	Excursion to the Pyramids (bus at the hotel). Informal discussions.
19:30–22:00	Informal excursion to the City Center (if there are any people interested). Bus from the main excursion passes by the hotel (approximate time).

Monday Computational Linguistics Formalisms I - Parsing and Syntactic Disambiguation - Semantics and Discourse - Language Documentation

08:10–08:50	Bus from hotel (leaves at 08:10, arrives at 08:50)
08:40–09:35	Registration
09:40–09:55	Inauguration
10:00–10:55	Keynote talk: An Overview of Probabilistic Tree Transducers for Natural Language Processing	Kevin Knight and Jonathan Graehl	1
11:00–1105	Break
Computational Linguistics Formalisms I
11:10–11:30	Modelling Grammatical and Lexical Knowledge: A Declarative Approach	Palmira Marrafa	38
11:35–11:55	Constructing a Parser for Latin	Cornelis H.A. Koster	49
12:00–11:05	Break
12:10–12:30	Parsing Korean Case Phenomena in a Type-Feature Structure Grammar	Jong-Bok Kim and Jaehyung Yang	61
12:35–12:55	A Computational Model of the Spanish Clitic System	Luis A. Pineda, Ivan V. Meza	73
13:00–13:55	Lunch
Parsing and Syntactic Disambiguation
14:00–14:30	Best paper award (2nd place): Unsupervised Evaluation of Parser Robustness	Johnny Bigert, Jonas Sjöbergh, Ola Knutsson, and Magnus Sahlgren	141
14:35–14:55	Regional vs. Global Finite-State Error Repair	Manuel Vilares, Juan Otero, and Jorge Graña	119
15:00–15:20	Mutual Information Independence Model using Kernel Density Estimation for Segmenting and Labeling Sequential Data	ZHOU GuoDong, YANG LingPeng, SU Jian, JI DongHong	153
15:25–15:30	Break
15:35–15:55	Applying Conditional Random Fields to Chinese Shallow Parsing	Yongmei Tan, Tianshun Yao, Qing Chen and Jingbo Zhu	165
16:00–16:20	Distributional Thesaurus vs. WordNet: A Comparison of Backoff Techniques for Unsupervised PP Attachment	Hiram Calvo, Alexander Gelbukh , Adam Kilgarriff	172
Language Documentation
16:25–16:45	Language Documentation: the Nahuatl Grammar	Mike Maxwell, Jonathan D. Amith	464
16:50–16:55	Break
17:00–18:55	Poster and Demo Session combined with Welcome Party
19:00–19:40	Bus to hotel (approximate time)

Tuesday Morphology - WSD - Lexical Resources - Machine Translation I: UNL - Speech and Natural Language Interfaces: UNL

08:10–08:50	Bus from hotel (leaves at 08:10, arrives at 08:50)
09:00–09:55	Keynote talk: Towards Developing Probabilistic Generative Models for Reasoning with Natural Language Representations	Daniel Marcu and Ana-Maria Popescu	87
10:00–10:05	Break
Morphology
10:10–10:30	Automatic Recognition of Czech Derivational Prefixes	Alfonso Medina Urrea and Jaroslava Hlaváčová	184
10:35–10:55	Word Extraction Based on Semantic Constraints in Chinese Word-formation	Maosong Sun, Shengfen Luo, and Benjamin K T’sou	197
Word Sense Disambiguation
11:00–11:20	Name Discrimination by Clustering Similar Contexts	Ted Pedersen, Amruta Purandare, and Anagha Kulkarni	221
11:25–11:30	Break
11:35–11:55	Multiwords and Word Sense Disambiguation	Victoria Arranz, Jordi Atserias and Mauro Castillo	245
12:00–12:20	Two Web-based Approaches for Noun Sense Disambiguation	Paolo Rosso, Manuel Montes-y-Gómez, Davide Buscaldi, Aarón Pancardo-Rodríguez, and Luis Villaseñor Pineda	261
Lexical Resources
12:25–12:45	Automatic Synonym Acquisition Based on Matching of Definition Sentences in Multiple Dictionaries	Masaki Murata, Toshiyuki Kanamaru, and Hitoshi Isahara	285
12:50–13:45	Lunch
13:50–14:20	Best paper award (1st place): Finding Instance Names and Alternative Glosses on the Web: WordNet Reloaded	Marius Paşca	273
14:25–14:45	Customisable Semantic Analysis of Texts	Vivi Nastase and Stan Szpakowicz	304
14:50–15:10	ITOLDU, a Web Service to Pool Technical Lexical Terms in a Learning Environment and Contribute to Multilingual Lexical Databases	Valérie Bellynck, Christian Boitet, John Kenwright	316
15:15–15:20	Break
Machine Translation I: UNL
15:25–15:45	The UNL Initiative: An Overview	Igor Boguslavsky; Jesús Cardeñosa; Carolina Gallardo; Luis Iraola	369
Speech and Natural Language Interfaces: UNL
15:50–16:10	VoiceUNL: a Semantic Representation of Emotions within Universal Networking Language Formalism Based on a Dialogue Corpus Analysis	Mutsuko Tomokiyo, Gérard Chollet	431
16:15–16:20	Break
16:25–18:20	Combined special event (topic to be announced)	Kevin Knight and Daniel Marcu
18:30–19:10	Bus to hotel (approximate time)

Wednesday Workshop program - Cultural program

09:00–18:00	UNL Workshop. See the Workshop Program. Bus at the hotel leaves at 08:10. Duration indicated here is approximate.
07:00–23:30	Excursion to the Butterfly Wintering site (bus at the hotel, , leaves at 07:00). Informal discussions.
09:00–18:00	Informal excursion to the City and Anthropological Museum (if there are any people interested). No bus is provided. Duration is very approximate.

Thursday Question Answering - Information Extraction - Information Retrieval - Text Classification, Categorization, and Clustering

08:10–08:50	Bus from hotel (leaves at 08:10, arrives at 08:50)
09:00–09:55	Keynote talk: Creating Subjective and Objective Sentence Classifiers from Unannotated Texts	Janyce Wiebe and Ellen Riloff	476
10:00–10:05	Break
Question Answering
10:10–10:30	Question Classification in Spanish and Portuguese	Thamar Solorio, Manuel Pérez-Coutiño, Manuel Montes-y-Gómez, Luis Villaseñor-Pineda, and Aurelio López-López	601
Information Extraction
10:35–10:55	Instance Pruning by Filtering Uninformative Words: an Information Extraction Case Study	Alfio Massimiliano Gliozzo, Claudio Giuliano, and Raffaella Rinaldi	488
11:00–11:20	Incremental Information Extraction Using Tree-based Context Representations	Christian Siefkes	500
11:25–11:30	Break
11:35–11:55	A Machine Learning Approach to Information Extraction	Alberto Téllez-Valero, Manuel Montes-y-Gómez, Luis Villaseñor-Pineda	528
12:00–12:20	Automatic Time Expression Labeling for English and Chinese Text	Kadri Hacioglu, Ying Chen, Benjamin Douglas	537
12:25–12:45	Integrating Natural Language Techniques in OO-Method	Isabel Díaz, Lidia Moreno, Inmaculada Fuentes, and Oscar Pastor	549
12:50–13:45	Lunch
13:50–14:20	Best paper award (3rd place): Learning Information Extraction Rules for Protein Annotation from Unannotated Corpora	Jee-Hyub Kim and Melanie Hilario	512
Information Retrieval
14:25–14:45	Document Re-ordering Based on Key Terms in Top Retrieved Documents	Yang Lingpeng, Ji Donghong, Nie Yu, Zhou Guodong	561
14:50–15:10	Merging Case Relations into VSM to Improve Information Retrieval Precision	Wang Hongtao, Sun Maosong, Liu Shaoming	573
Semantics and Discourse
15:15–15:35	Putting Pieces Together: Combining FrameNet, VerbNet and WordNet for Robust Semantic Parsing	Lei Shi and Rada Mihalcea	99
15:40–15:45	Break
Text Classification, Categorization, and Clustering
15:50–16:10	Techniques for Improving the Performance of Naive Bayes for Text Classification	Karl-Michael Schneider	670
16:15–16:35	Efficient Modeling of Analogy	Lars G. Johnsen and Christer Johansson	682
16:40–17:00	A Supervised Clustering Method for Text Classification	Umarani Pappuswamy, Dumisizwe Bhembe, Pamela W. Jordan and Kurt VanLehn	692
17:05–17:10	Break
17:15–18:10	Special event (topic to be announced)	Ellen Riloff
18:25–19:05	Bus to hotel (approximate time)
Friday Natural Language Generation - Machine Translation II - Computational Linguistics Formalisms II - Language Identification - Summarization - Named Entity Recognition - Spelling and Style Checking

08:10–08:50	Bus from hotel (leaves at 08:10, arrives at 08:50)
09:00–09:55	Keynote talk: Message Automata for Messages with Variants, and Methods for their Translation	Christian Boitet	349
10:00–10:05	Break
Natural Language Generation
10:10–10:30	Evaluating Evaluation Methods for Generation in the Presence of Variation	Amanda Stent, Matthew Marge, and Mohit Singhai	333
Machine Translation II
10:35–10:55	Interactive Resolution of Intrinsic and Translational Ambiguity in a Machine Translation System	Igor M. Boguslavsky, Leonid L. Iomdin, Alexander V. Lazursky, Leonid G. Mityushin, Victor G. Sizov, Leonid G. Kreydlin, Alexander S. Berdichevsky	380
11:00–11:20	Chinese-Japanese Clause Alignment	Xiaojie Wang, Fuji Ren	392
11:25–11:30	Break
11:35–11:55	Direct Combination of Spelling and Pronunciation Information for Robust Back-Transliteration	Slaven Bilac and Hozumi Tanaka	403
Computational Linguistics Formalisms II
12:00–12:20	A Modular Account of Information Structure in Extensible Dependency Grammar	Ralph Debusmann, Oana Postolache, and Maarika Traat	26
Language Identification
12:25–12:45	Disentangling from Babylonian Confusion – Unsupervised Language Identification	Chris Biemann, Sven Teresniak	762
12:50–13:45	Lunch
Summarization
13:50–14:10	Summarisation through Discourse Structure	Dan Cristea, Oana Postolache, and Ionuţ Pistol	621
14:15–14:35	Automatic Annotation of Corpora for Text Summarisation: A Comparative Study	Constantin Orăsan	658
Named Entity Recognition
14:40–15:00	Resolution of Data Sparseness in Named Entity Recognition using Hierarchical Features and Feature Relaxation Principle	ZHOU GuoDong, SU Jian, YANG LingPeng	739
15:05–15:25	Learning Named Entity Recognition in Portuguese from Spanish	Thamar Solorio and Aurelio López López	751
15:30–15:35	Break
Spelling and Style Checking
15:40–16:00	Design and Development of a System for the Detection of Agreement Errors in Basque	Arantza Díaz de Ilarraza, Koldo Gojenola and Maite Oronoz	782
16:05–16:25	An Experiment in Detection and Correction of Malapropisms through the Web	Igor A. Bolshakov	792
16:30–16:50	A Paragraph Boundary Detection System	Dmitriy Genzel	805
16:55–17:00	Break
17:05–18:00	Special event (topic to be announced)	Christian Boitet
18:05–18:10	Best Presentation & Best Poster Award and Closing ceremony
18:25–19:05	Bus to hotel (approximate time)


Saturday Cultural program

09:00–19:30	Excursion to the Cave and Xochicalco pyramids (bus at the hotel, leaves at 09:00). Informal discussions.

Poster presentations

All posters will be presented on Monday evening

Title	Authors	Page

A Parallel Approach to Syllabification	Anca Dinu and Liviu P. Dinu	83
Assigning Function Tags with a Simple Model	Vasile Rus and Kirtan Desai	111
Finding Discourse Relations in Student Essays	Rohana Mahmud and Allan Ramsay	115
Korma 2003: Newly Improved Korean Morpheme Analysis Module for Reducing Terminological and Spacing Errors in Document Analysis	Ho-cheol Choi and Sang-yong Han	193
Using Directed Graph based BDMM Algorithm for Chinese Word Segmentation	Yaodong Chen, Ting Wang, and Huowang Chen	209
Entity-Based Noun Phrase Coreference Resolution	Xiaofeng Yang, Jian Su, and Lingpeng Yang	213
The Right Frontier Constraint as Conditional	Claudia Sassen and Peter Kühnlein	217
Word Sense Disambiguation by Semi-Supervised Learning	Zheng-Yu Niu, Dong-Hong Ji, Chew-Lim Tan, and Ling-Peng Yang	233
Crossing Parallel Corpora and Multilingual Lexical Databases for WSD	Alfio Massimiliano Gliozzo, Marcello Ranieri, and Carlo Strapparava	237
A Mapping between Classifiers and Training Conditions for WSD	Aarón Pancardo-Rodríguez, Manuel Montes-y-Gómez, Luis Villaseñor-Pineda, Paolo Rosso	241
Context Expansion with Global Keywords for a Conceptual Density-Based WSD	Davide Buscaldi, Paolo Rosso, and Manuel Montes y Gómez	257
Enriching WordNet with Derivational Subnets	Karel Pala and Radek Sedláček	297
Building a Situation-based Language Knowledge Base	Qiang ZHOU, Zushun CHEN	325
Unsupervised Learning of P NP P Word Combinations	Sofía N. Galicia-Haro, Alexander Gelbukh	329
Reconciling Parameterization, Configurability and Optimality in Natural Language Generation via Multiparadigm Programming	Jorge Marques Pelizzoni, Maria das Graças Volpe Nunes	344
On a Pitch Detection Method Using Noise Reduction	Jong Kuk Kim, Ki Young Lee, Myung Jin Bae	419
Toward Acoustic Models for Languages with Limited Linguistic Resources	Luis Villaseñor-Pineda, Viet Bac Le, Manuel Montes-y-Gómez, and Manuel Pérez-Coutiño	423
A Study On Pitch Detection in Time-Frequency Hybrid Domain	Wangrae Jo, Jongkuk Kim, Myungjin Bae	427
Transformation-Based Information Extraction Using Learned Meta-Rules	Un Yong Nahm	524
Retrieval Efficiency of Normalized Query Expansion	Sofia Stamou and Dimitris Christodoulakis	593
Selecting Interesting Articles Using Their Similarity Based Only on Positive Examples	Jiří Hroza and Jan Žižka	597
Learning the Query Generation Patterns	Marcin Skowron and Kenji Araki	609
Exploiting Question Concepts for Query Expansion	Hae-Jung Kim, Ki-Dong Bu, Junghyun Kim and Sang-Jo Lee	613
Experiment on Combining Sources of Evidence for Passage Retrieval	Alexander Gelbukh, NamO Kang, SangYong Han	617
LexTrim: A Lexical Cohesion based Approach to Parse-and-Trim Style Headline Generation	Ruichao Wang, Nicola Stokes, William Doran, Eamonn Newman, John Dunnion, Joe Carthy	633
Extractive Summarization Based on Word Information and Sentence Position	Carlos MÉNDEZ Cruz and Alfonso MEDINA Urrea	641
Automatic Extraction and Learning of Keyphrases from Scientific Articles	Yaakov HaCohen-Kerner, Zuriel Gross, Asaf Masa	645
Enhancement of DTP Feature Selection Method for Text Categorization	Edgar Moyotl-Hernández, Héctor Jiménez-Salazar	707
A Method of Rapid Prototyping of Evolving Ontologies	Pavel Makagonov, Alejandro Ruiz Figueroa	735
On the Syllabic Similarities of Romance Languages	Anca Dinu and Liviu P. Dinu	774

Canceled Talks

Title	Authors	Page

Lexicalized Beam Thresholding Parsing with Prior and Boundary Estimates	Deyi Xiong, Qun Liu, and Shouxun Lin	131
Combining Multiple Statistical Classifiers to Improve the Accuracy of Task Classification	Wei-Lin Wu, Ru-Zhan Lu, Feng Gao, Yan Yuan	442
A Finite State Network for Phonetic Text Processing	Edward John Garrett	453
FASiL Adaptive Email Categorization System	Yunqing Xia, Angelo Dalli, Yorick Wilks, Louise Guthrie	711
A Prosodic Diphone Database for Korean Text-to-Speech Synthesis System	Kyuchul Yoon	415
Evaluating Document-to-document Relevance based on Document Language Model: Modeling, Implementation and Performance Evaluation	Ge Yu, Xiaoguang Li, Yubin Bao, Daling Wang	582
ESPClust: An Effective Skew Prevention Method for Model-based Document Clustering	Xiaoguang Li, Ge Yu, Daling Wang, Yubin Bao	723
Automatic Language Identification Using Multivariate Analysis	Vinosh Babu James J. and Baskaran Sankaran	778
A Simple Rule-based Approach to Organization Name Recognition in Chinese Text	Houfeng Wang and Wuguang Shi	758
Unsupervised Text Classification using Kohonen’s Self Organizing Network	Nirmalya Chowdhury and Diganta Saha	703
Generating Headline Summary from a Document Set	Kamal Sarkar, Sivaji Bandyopadhyay	637