Memory-Based models of inflectional morphology acquisition and processing
author:
Walter Daelemans,
+Center for Dutch Language and Speech, Department of Linguistics, University of Antwerp
Description
Old and recent results using Memory-Based Learning in inflectional morphology (Pinker: fruit fly of psycholinguistics). Memory-based learning with TiMBL: learning is storage. Cases: English and Dutch past tense; more interesting: German plural and Dutch plural. Computational psycholinguistics methodology.
You might be experiencing some problems with Your Video player.
| Slides | |
| 0:00 | Memory-Based Models of inflectional morphology acquisition and processing |
| 0:03 | Contents |
| 1:21 | Nature of the human language processing architecture |
| 3:33 | Machine Learning |
| 5:02 | Supervised Learners |
| 8:08 | Eager vs Lazy Learning |
| 11:18 | Visualizing disjunctivity |
| 12:55 | English Past Tense: Words + Rules |
| 14:27 | Prasada & Pinker Data |
| 15:07 | Memory-Based Alternative |
| 16:22 | Prasada & Pinker Data |
| 16:31 | Memory-Based Alternative |
| 16:42 | Prasada and Pinker Simulation |
| 18:04 | Replication Study in Dutch |
| 18:14 | Memory-based learning and classification |
| 18:42 | Similarity / distance |
| 20:06 | The MVDM distance function |
| 20:49 | Distance weighted class voting |
| 22:04 | Exemplar weighting |
| 22:21 | TiMBL http://ilk.uvt.nl/timbl |
| 22:36 | Back to Inflectional Morphology: German Plural - part 1 |
| 24:11 | Back to Inflectional Morphology: German Plural - part 2 |
| 24:23 | The default status of -s |
| 24:52 | Data & Representation |
| 25:18 | Feature Relevance Computation |
| 25:36 | Clustering on MVDM materices |
| 26:55 | Acquisition Data: Summary of previous studies |
| 27:55 | Learnability |
| 29:10 | MBL simulation |
| 30:38 | Bartke, Marcus, Clahsen (1995) |
| 32:19 | MBL simulation |
| 32:58 | Discussion |
| 34:40 | The Dutch plural |
| 35:17 | What is the default process in Dutch plural inflection? |
| 35:42 | The Dual-Mechanism Model for Dutch Plural Inflection |
| 36:14 | Inflecting non-canonical roots |
| 36:35 | Methodology: what is a good model? |
| 38:54 | MBL model of Dutch plural inflection - part 1 |
| 40:10 | MBL model of Dutch plural inflection - part 2 |
| 40:49 | MBL model of Dutch plural inflection - part 3 |
| 41:19 | Results - part 1 |
| 42:03 | Results - part 2 |
| 42:21 | Results - part 3 |
| 42:55 | Results - part 4 |
| 43:25 | Results - part 5 |
| 44:58 | Results - part 6 |
| 45:01 | Results - part 7 |
| 45:34 | Results - part 8 |
| 45:37 | Results - part 10 |
| 46:16 | Conclusions |
| 47:21 | Additional work with TiMBL |
Lecture rating
| People found this lecture: | ||
| Worth seeing | ||
| because it is: | ||
| Valuable and informative | ||
| Well presented | ||
| Easily understandable | ||
| Acceptably recorded | ||
| You need to login to cast your vote. | ||
Report a problem or upload files
If you have found a problem with this lecture or would like to send us extra material, articles, exercises, etc., please use our ticket system to describe your request and upload the data.Enter your e-mail into the 'Cc' field, and we will keep you updated with your request's status.
Related content
Visitors who watched this lecture also watched...
Link this page
Would you like to put a link to this lecture on your homepage?Go ahead! Copy the HTML snippet !





