I7 Logo
Chair for Foundations of Software Reliability and Theoretical Computer Science
Informatik Logo TUM Logo
Publications - Fast and Accurate Unlexicalized Parsing via Structural Annotations

Reference:

M. Schlund, M. Luttenberger, and J. Esparza. Fast and Accurate Unlexicalized Parsing via Structural Annotations. In Proceedings of the 14th Conference of the European Chapter of the Association for Computational Linguistics, volume 2: Short Papers, pages 164–168, Gothenburg, Sweden, April 2014. Association for Computational Linguistics.

Abstract:

We suggest a new annotation scheme for unlexicalized PCFGs that is inspired by formal language theory and only depends on the structure of the parse trees. We evaluate this scheme on the TüBa-D/Z treebank w.r.t. several metrics and show that it improves both parsing accuracy and parsing speed considerably. We also show that our strategy can be fruitfully combined with known ones like parent annotation to achieve accuracies of over labeled and leaf-ancestor score. Despite increasing the size of the grammar, our annotation allows for parsing more than twice as fast as the PCFG baseline.

Suggested BibTeX entry:

@inproceedings{SLE14,
    address = {Gothenburg, Sweden},
    author = {M. Schlund and M. Luttenberger and J. Esparza},
    booktitle = {Proceedings of the 14th Conference of the European Chapter of the Association for Computational Linguistics, volume 2: Short Papers},
    month = {April},
    pages = {164--168},
    publisher = {Association for Computational Linguistics},
    title = {Fast and {A}ccurate {U}nlexicalized {P}arsing via {S}tructural {A}nnotations},
    year = {2014}
}

PDF (182 kB)
See www.aclweb.org ...