|
Teaching GuideTerm Faculty of Computer Science |
| Grao en Ciencia e Enxeñaría de Datos |
 Subjects |
| Natural Language Processing and Text Mining |
| Contents |
| Identifying Data | 2022/23 | |||||||||||||
| Subject | Natural Language Processing and Text Mining | Code | 614G02043 | |||||||||||
| Study programme |
|
|||||||||||||
| Descriptors | Cycle | Period | Year | Type | Credits | |||||||||
| Graduate | 2nd four-month period |
Fourth | Optional | 6 | ||||||||||
|
||||||||||||||
| Topic | Sub-topic |
| Constituent parsing for text mining | Syntax of constituents Statistical constituent analysis with dynamic programming Analysis of shift-reduce constituents with neural networks Analysis of discontinuous constituents Sequence-by-sequence constituent analysis |
| Dependency parsing for text mining |
Dependency Syntax Annotation criteria and universal dependencies Dependency analysis based on transitions Analysis of dependencies based on graphs Non-projectivity |
| Semantics | Analysis of semantic dependencies Dense vectors using SVD Dense vectors using word prediction: skip-gram and CBOW Properties of dense vectors Brown clustering |
| Computing with word senses | Word senses Relations between senses Databases of lexical relationships Disambiguation of the meaning of words |
| Practical applications of text mining | - |
| Multilingual language processing | Processing of morphologically-rich languages Non-segmented language processing Language processing with few resources Translingual processing |
| Emerging technologies | - |
|
