| Friday, November 3, 2006 | |
|---|---|
| UTC 3.124 (before lunch), UTC 3.104 (after lunch) | |
| 8:30 - 9:15 | Registration / Coffee and refreshments |
| 9:15 - 9:30 | Opening remarks |
| 9:30 - 10:45 |
Keynote address Linguistic Data Management with the Natural Language Toolkit Steven Bird, University of Melbourne, University of Pennsylvania |
| 10:45 - 10:50 | Mini-break |
| 10:50 - 11:20 |
Annotating and archiving natural language paradigms online Dorothee Beermann & Atle Prange |
| 11:20 - 11:50 |
The SIL FieldWorks Language Explorer Approach to Morphological Parsing H. Andrew Black & Gary F. Simons |
| LUNCH (on your own, 70 minutes) | |
| Please note change of location: Moving to UTC 3.104 | |
| 1:00 - 1:30 |
A Method for Enhancing Search Using Transliteration of Mandarin Chinese Vijay John PDF of paper |
| 1:30 - 2:00 |
Inflectional Vocalization of Arabic Text: A MaxEnt Tagging Approach Frederick M. Hoyt |
| 2:05 - 2:10 | Mini-break |
| 2:10 - 3:35 |
Keynote address Cutting Corpus Costs: Machine Learning and Annotation Jason Baldridge , University of Texas at Austin |
| 3:35 - 3:50 | Break |
| 3:50 - 5:30 |
Panel Discussion Understanding needs of documentary and descriptive linguistics, gaps in the current tool set, problems of current technologies, issues involved in doing work on less-studied languages Tony Woodbury, moderator |
| Saturday, November 4, 2006 | |
| CAL 100 | |
| 9:00 - 10:15 |
Keynote address The Grammar Matrix: A Crosslinguistic Resource to Promote Grammar Engineering for Linguistic Hypothesis Testing Emily Bender, University of Washington |
| 10:15 - 10:20 | Mini-break |
| 10:20 - 10:50 |
Two Approaches to Mayan Grammar Development in CCG Elias Ponvert |
| 10:50 - 11:20 |
A Combinatory Categorial Grammar of a Fragment of American Sign Language Tony Wright |
| 11:20 - 11:50 |
A Morphological Analyzer for Verbal Aspect in American Sign Language Aaron Shield & Jason Baldridge |
| LUNCH (on your own, 70 minutes) | |
| 1:00 - 2:15 |
Keynote address Detecting outliers: useful for word sense assignment - and for aiding manual annotation? Katrin Erk, University of Texas at Austin |
| 2:15 - 2:20 | Mini-break |
| 2:20 - 2:50 |
Affix Discovery based on Entropy and Economy Measurements Alfonso Medina-Urrea |
| 2:50 - 3:20 |
Enriching Language Data through Projected Structures William Lewis, Fei Xia, & Dan Jinguji |
| 3:20 - 3:50 |
Finite State Methods for Bantu Verb Morphology Robert Elwell |
| 3:50 - 4:05 | Break |
| 4:05 - 5:20 |
Keynote address Maximizing the Utility of Small Training Sets in Machine Learning Ray Mooney, University of Texas at Austin PPT SLIDES |
| Sunday, November 5, 2006 | |
| CAL 100 | |
| 9:00 - 10:15 |
Keynote address The problems of scale in language documentation Mark Liberman, University of Pennsylvania |
| 10:15 - 10:30 | Break |
| 10:30 - 12:30 | Panel Discussion How can computational linguistics address the needs of documentary and descriptive linguistics, and how will doing so further the state of research in the field of computational linguistics? What are fruitful directions for future research? Where do we go from here? |
| Alternate |
Using POS Tags in Word Prediction: A Statistical Language Modeling for the Persian Language Masood Ghayoomi & Ehsan Daroodi |