Using foreign inclusion detection to improve parsing performance

Beatrice Alex; Amit Dubey; Frank Keller

Using foreign inclusion detection to improve parsing performance

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract / Description of output

Inclusions from other languages can be a significant source of errors for monolin-
gual parsers. We show this for English inclusions, which are sufficiently frequent to
present a problem when parsing German. We describe an annotation-free approach for accurately detecting such inclusions, and develop two methods for interfacing this approach with a state-of-the-art parser for German. An evaluation on the TIGER corpus shows that our inclusion entity model achieves a performance gain of 4.3 points in F-score over a baseline of no inclusion detection, and even outperforms a parser with access to gold standard part-of-speech tags.

Original language	English
Title of host publication	Proceedings of EMNLP-CoNLL 2007
Number of pages	10
Publication status	Published - 2007

Keywords / Materials (for Non-textual outputs)

seer,

Access to Document

Alex_Alex et al 2007 Using Foreign Inclusion DetectionFinal published version, 87.5 KB

http://acl.ldc.upenn.edu/D/D07/D07-1016.pdf

Cite this

@inproceedings{6b8df6e9705a43bebdce8b612e39e71d,

title = "Using foreign inclusion detection to improve parsing performance",

abstract = "Inclusions from other languages can be a significant source of errors for monolin-gual parsers. We show this for English inclusions, which are sufficiently frequent topresent a problem when parsing German. We describe an annotation-free approach for accurately detecting such inclusions, and develop two methods for interfacing this approach with a state-of-the-art parser for German. An evaluation on the TIGER corpus shows that our inclusion entity model achieves a performance gain of 4.3 points in F-score over a baseline of no inclusion detection, and even outperforms a parser with access to gold standard part-of-speech tags.",

keywords = "seer,",

author = "Beatrice Alex and Amit Dubey and Frank Keller",

year = "2007",

language = "English",

booktitle = "Proceedings of EMNLP-CoNLL 2007",

}

TY - GEN

T1 - Using foreign inclusion detection to improve parsing performance

AU - Alex, Beatrice

AU - Dubey, Amit

AU - Keller, Frank

PY - 2007

Y1 - 2007

N2 - Inclusions from other languages can be a significant source of errors for monolin-gual parsers. We show this for English inclusions, which are sufficiently frequent topresent a problem when parsing German. We describe an annotation-free approach for accurately detecting such inclusions, and develop two methods for interfacing this approach with a state-of-the-art parser for German. An evaluation on the TIGER corpus shows that our inclusion entity model achieves a performance gain of 4.3 points in F-score over a baseline of no inclusion detection, and even outperforms a parser with access to gold standard part-of-speech tags.

AB - Inclusions from other languages can be a significant source of errors for monolin-gual parsers. We show this for English inclusions, which are sufficiently frequent topresent a problem when parsing German. We describe an annotation-free approach for accurately detecting such inclusions, and develop two methods for interfacing this approach with a state-of-the-art parser for German. An evaluation on the TIGER corpus shows that our inclusion entity model achieves a performance gain of 4.3 points in F-score over a baseline of no inclusion detection, and even outperforms a parser with access to gold standard part-of-speech tags.

KW - seer,

M3 - Conference contribution

BT - Proceedings of EMNLP-CoNLL 2007

ER -

Using foreign inclusion detection to improve parsing performance

Abstract / Description of output

Keywords / Materials (for Non-textual outputs)

Access to Document

Fingerprint

Cite this