Joint Morphological and Syntactic Analysis

Add to your list(s) Download to your calendar using vCal

• Bernd Bohnet, University of Birmingham
• Thursday 03 October 2013, 16:00-17:00
• UG05, Learning Centre.

If you have a question about this talk, please contact Christine Zarges.

Please note that coffee will be served at 3:15 at room 123 (School of Computer Science), followed by the one-hour seminar at 4pm.

Starting from a dependency parsing approach, we explore different ways of integrating morphological features into the model. We proposed joint morphological and syntactic analysis as a way of improving parsing accuracy for richly inflected languages. We also investigate the use of morphological analyzers to provide constraints and the use of word clusters. Evaluation on five morphologically rich languages shows consistent improvements in both morphological and syntactic accuracy for joint prediction over a pipeline model, with further improvements due to lexical constraints. The final results improve the state of the art in dependency parsing for all five languages.

This talk is part of the Computer Science Departmental Series series.

This talk is included in these lists:

• Computer Science Departmental Series
• Computer Science Distinguished Seminars
• UG05, Learning Centre
• computer sience

Note that ex-directory lists are not shown.