Year: 2009
Type: conference-paper
Abstract: We compare two approaches to dependency tree linearization, a task which arises in many NLP applications. The first one is the widely used 'overgenerate and rank' approach which relies exclusively on a trigram language model (LM); the second one combines language modeling with a maximum entropy classifier trained on a range of linguistic features. The results provide strong support for the combined method and show that trigram LMs are appropriate for phrase linearization while on the clause level a richer representation is necessary to achieve comparable performance.
Authors: Katja Filippova, Michael Strube
Institution: European Media Laboratory (Germany)
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
Funder: Klaus Tschira Stiftung
OpenAlex ID: W1965703460