| Title: | Extracting terminologically relevant collocations from texts on informatics |
|---|
| Authors: | ID Gmeiner, Primož (Author)
ID Plemenitaš, Katja (Mentor) More about this mentor...  |
|---|
| Files: |  UNI_Gmeiner_Primoz_2010.pdf (914,91 KB)
MD5: 25C281BC48AC5DCCF6F3024EE4F1DBE6
PID: 20.500.12556/dkum/23efa0d1-ff78-44a6-8bec-f4bdbe9a248d
|
|---|
| Language: | English |
|---|
| Work type: | Undergraduate thesis |
|---|
| Organization: | FF - Faculty of Arts
|
|---|
| Abstract: | The diploma thesis discusses the methodology behind the extraction of terminologically relevant collocations from texts on informatics, particularly from the special subject domain of electronic government. The theoretical framework presents a network of scientific fields crucial in understanding of basic facts surrounding the collocation extraction. Empirical part of the thesis, however, is a more hands-on approach describing how the extraction is performed in practice. Key aspects of the research are presented in an orderly fashion. A hybrid method of syntactic pattern filtering and statistical calculations is presented. It is divided into several stages and described in detail. The scale of the research included extraction method, data import, statistical analysis, corpora analysis and glossary-building. The research was carried out in a semi-automatic way, i.e. some work was done manually, while everything else was computer-assisted. The glossary created is an alphabetical word-list of two-word terminological collocations accompanied by their Slovene equivalents and definitions. It is a basic construct that can later on enable me to supplement the existing two-word units with the expansion of their n-grams, thus creating a glossary with multi-word units the collocation extraction has provided me with. |
|---|
| Keywords: | terminološke kolokacije (sopojavljanke), luščenje strokovnega izrazja z upoštevanjem kolokacij (sopojavljank), hibridna metoda, skladenjski vzorci, korpusna analiza, glosar (razlagalni slovar), elektronska uprava |
|---|
| Place of publishing: | Maribor |
|---|
| Publisher: | [P. Gmeiner] |
|---|
| Year of publishing: | 2010 |
|---|
| PID: | 20.500.12556/DKUM-14232 |
|---|
| UDC: | 811.111'25(043.2):004 |
|---|
| COBISS.SI-ID: | 17788680 |
|---|
| NUK URN: | URN:SI:UM:DK:DLG9M4VK |
|---|
| Publication date in DKUM: | 23.07.2010 |
|---|
| Views: | 2721 |
|---|
| Downloads: | 251 |
|---|
| Metadata: |    |
|---|
| Categories: | FF
|
|---|
|
:
|
Copy citation |
|---|
| | | | Average score: | (0 votes) |
|---|
| Your score: | Voting is allowed only for logged in users. |
|---|
| Share: |  |
|---|
Hover the mouse pointer over a document title to show the abstract or click
on the title to get all document metadata. |
