Parsing Any Domain English text to CoNLL dependencies

Sudheer Kolachina, Prasanth Kolachina


Abstract
It is well known that accuracies of statistical parsers trained over Penn Treebank on test sets drawn from the same corpus tend to be overestimates of their actual parsing performance. This gives rise to the need for evaluation of parsing performance on corpora from different domains. Evaluating multiple parsers on test sets from different domains can give a detailed picture about the relative strengths/weaknesses of different parsing approaches. Such information is also necessary to guide choice of parser in applications such as machine translation where text from multiple domains needs to be handled. In this paper, we report a benchmarking study of different state-of-art parsers for English, both constituency and dependency. The constituency parser output is converted into CoNLL-style dependency trees so that parsing performance can be compared across formalisms. Specifically, we train rerankers for Berkeley and Stanford parsers to study the usefulness of reranking for handling texts from different domains. The results of our experiments lead to interesting insights about the out-of-domain performance of different English parsers.
Anthology ID:
L12-1652
Volume:
Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12)
Month:
May
Year:
2012
Address:
Istanbul, Turkey
Editors:
Nicoletta Calzolari, Khalid Choukri, Thierry Declerck, Mehmet Uğur Doğan, Bente Maegaard, Joseph Mariani, Asuncion Moreno, Jan Odijk, Stelios Piperidis
Venue:
LREC
SIG:
Publisher:
European Language Resources Association (ELRA)
Note:
Pages:
3873–3880
Language:
URL:
http://www.lrec-conf.org/proceedings/lrec2012/pdf/1097_Paper.pdf
DOI:
Bibkey:
Cite (ACL):
Sudheer Kolachina and Prasanth Kolachina. 2012. Parsing Any Domain English text to CoNLL dependencies. In Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12), pages 3873–3880, Istanbul, Turkey. European Language Resources Association (ELRA).
Cite (Informal):
Parsing Any Domain English text to CoNLL dependencies (Kolachina & Kolachina, LREC 2012)
Copy Citation:
PDF:
http://www.lrec-conf.org/proceedings/lrec2012/pdf/1097_Paper.pdf