Neural Methods in NLP
|Master||SS-CL, SS-FAL||8 LP|
|Zeit und Ort|| 10:00–17:00 Uhr
27., 29., 30., 31.3: INF 325. SR 7
Dienstag 28.3.: INF 326 SR 28
- Mathematische Grundlagen der CL
- Statistical Methods for CL
- Lektüre und aktive Teilnahme
- Hausarbeit oder Projekt
In the seminar we will investigate neural NLP methods and how they are applied in a variety of NLP tasks, and compare them to traditional methods for these tasks.
Phenomena will include
- sequence labeling problems (POS tagging, supertagging, NER)
- structure prediction tasks such as parsing, SRL, or semantic parsing
- word embeddings and their use in sense disambiguation or lexical acquisition tasks
- coreference resolution
- NL generation
- higher-level NLP applications, such as question answering, reading comprehension or inferencing tasks
Based on the discussed papers we will construct a chart of system architectures and variations that characterize successful systems.
- The list of papers to be discussed in the seminar will be published by Feb. 28th on this page.
- Seminar participants have to register from 13th to 17th of March by email, with a list of at least 3 candidate papers for presentation.
Introductory material to Deep Learning: