Standard architectures favor sequential processes for the semantic and syntactic part of natural language generation. Some semantic decisions, however, require information from the syntactic part, as is shown at the example of translating English gerunds into German. As a solution to this problem, a model is proposed in which syntactic and semantic modules work in parallel, computing preference values for different translation variants. On the basis of these preferences, one variant is selected and further elaborated. This model draws on a maximum of information, including stylistic considerations, while avoiding the computational load of backtracking processes.
| Identifer | oai:union.ndltd.org:DUETT/oai:DUETT:duett-12132001-142432 |
| Date | 13 December 2001 |
| Creators | Mehl, Stephan |
| Contributors | Hoeppner, Wolfgfang |
| Publisher | Gerhard-Mercator-Universitaet Duisburg |
| Source Sets | Dissertations and other Documents of the Gerhard-Mercator-University Duisburg |
| Language | German |
| Detected Language | English |
| Type | text |
| Format | application/pdf |
| Source | http://www.ub.uni-duisburg.de/ETD-db/theses/available/duett-12132001-142432/ |
| Rights | unrestricted, I hereby certify that, if appropriate, I have obtained and attached hereto a written permission statement from the owner(s) of each third party copyrighted matter to be included in my thesis, dissertation, or project report, allowing distribution as specified below. I certify that the version I submitted is the same as that approved by my advisory committee. Hiermit erteile ich der Universitaet Duisburg das nicht-ausschliessliche Recht unter den unten angegebenen Bedingungen, meine Dissertation, Staatsexamens- oder Diplomarbeit, meinen Forschungs- oder Projektbericht zu veroeffentlichen und zu archivieren. Ich behalte das Urheberrecht und das Recht das Dokument zu veroeffentlichen und in anderen Arbeiten weiterzuverwenden. |
Page generated in 0.0012 seconds