Parsing natural language is an essential step in several applications that involve document analysis, e.g. knowledge extraction, question answering, summarization, filtering. Using Maximum Entropy (Berger, et al. 1996) classifiers I built a parser that achieves a throughput of over 200 sentences per second, with a small loss in accuracy of about 2-3 %. I extended the Yamada-Matsumoto parser to handle labeled dependencies: I tried two approaches: using a single classifier to predict pairs of actions and labels and using two separate classifiers, one for actions and one for labels. Finally, I extended the repertoire of actions used by the parser, in order to handle non-projective relations. Tests on the PDT (Böhmovà et al., 2003) show that the added actions are sufficient to handle all cases of non-projectivity.
Experiments with a Multilanguage Non-Projective Dependency Parser
ATTARDI, GIUSEPPE
2006-01-01
Abstract
Parsing natural language is an essential step in several applications that involve document analysis, e.g. knowledge extraction, question answering, summarization, filtering. Using Maximum Entropy (Berger, et al. 1996) classifiers I built a parser that achieves a throughput of over 200 sentences per second, with a small loss in accuracy of about 2-3 %. I extended the Yamada-Matsumoto parser to handle labeled dependencies: I tried two approaches: using a single classifier to predict pairs of actions and labels and using two separate classifiers, one for actions and one for labels. Finally, I extended the repertoire of actions used by the parser, in order to handle non-projective relations. Tests on the PDT (Böhmovà et al., 2003) show that the added actions are sufficient to handle all cases of non-projectivity.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
