Thesis
Probabilistic modelling of morphologically rich languages
- Abstract:
-
This thesis investigates how the sub-structure of words can be accounted for in probabilistic models of language. Such models play an important role in natural language processing tasks such as translation or speech recognition, but often rely on the simplistic assumption that words are opaque symbols. This assumption does not fit morphologically complex language well, where words can have rich internal structure and sub-word elements are shared across distinct word forms.
Our appro...
Expand abstract
Actions
Authors
Contributors
+ Blunsom, P
Division:
MPLS
Department:
Computer Science
Role:
Supervisor
+ Pulman, S
Division:
MPLS
Department:
Computer Science
Role:
Supervisor
Bibliographic Details
- Publication date:
- 2014
- Type of award:
- DPhil
- Level of award:
- Doctoral
- Awarding institution:
- University of Oxford
Item Description
- Language:
- English
- Keywords:
- Subjects:
- UUID:
-
uuid:8df7324f-d3b8-47a1-8b0b-3a6feb5f45c7
- Local pid:
- ora:11837
- Deposit date:
- 2015-07-09
Terms of use
- Copyright holder:
- Botha, J
- Copyright date:
- 2014
- Notes:
- This thesis is not currently available via ORA.
- Licence:
- CC Attribution (CC BY)
If you are the owner of this record, you can report an update to it here: Report update to this record