Haagsma, H. (2013) Grammatical role and word order predict. Bachelor's Thesis, Artificial Intelligence.
|
Text
Hessel_Bsc_Version_3_22Aug2013.pdf - Published Version Download (159kB) | Preview |
|
![[img]](https://fse.studenttheses.ub.rug.nl/style/images/fileicons/text.png) |
Text
HaagsmaHAkkoordSpenader.pdf - Other Restricted to Registered users only Download (24kB) |
Abstract
In this project, a corpus study using crowd-sourced annotation was done to gain new insights in the distribution of two Finnish pronouns: the demonstrative tämä, ’this’, and the personal pronoun hän, ’s/he’. A non-tagged, non-annotated corpus was morphosyntactically tagged, the relevant pronouns were extracted and Wordrobe, a game-like, online system, which allows people with no linguistic or annotation expertise (but high language-competence) to use their knowledge for annotations, was used to acquire co-reference annotation. The expectation is that a significant relationship between grammatical role, linear word order and the usage of tämä and hän will be found, with tämä used for second-mentioned antecedents, and hän mainly used for subject antecedents. Results show low frequencies of OS-word order, so no clear distinction between the factors can be made. Sentences with only one argument and non-subject/object arguments were also studied, and an unexpectedly high number of tämä with intransitive subject antecedents, which cannot directly be explained. This warrants further study of these previously largely ignored sentence types.
| Item Type: | Thesis (Bachelor's Thesis) |
|---|---|
| Degree programme: | Artificial Intelligence |
| Thesis type: | Bachelor's Thesis |
| Language: | English |
| Date Deposited: | 15 Feb 2018 07:54 |
| Last Modified: | 15 Feb 2018 07:54 |
| URI: | https://fse.studenttheses.ub.rug.nl/id/eprint/11322 |
Actions (login required)
 |
View Item |