RoDEO: Reasoning over Dependencies Extracted Online

Reda Siblini, Leila Kosseim


Abstract
The web is the largest available corpus, which could be enormously valuable to many natural language processing applications. However it is becoming very difficult to identify relevant information from the web. We present a system for querying dependency tree collocations from the web. We show its usefulness in identifying relevant information by evaluating its accuracy in the task of extracting classes of named entities. The task achieved a general accuracy of 70%.
Anthology ID:
2008.wac-1.9
Volume:
Proceedings of the 4th Web as Corpus Workshop
Month:
June
Year:
2008
Address:
Marrakech, Morocco
Editors:
Stefan Evert, Adam Kilgarriff, Serge Sharoff
Venues:
WAC | WS
SIG:
Publisher:
European Language Resources Association
Note:
Pages:
55–62
Language:
URL:
https://preview.aclanthology.org/jlcl-multiple-ingestion/2008.wac-1.9/
DOI:
Bibkey:
Cite (ACL):
Reda Siblini and Leila Kosseim. 2008. RoDEO: Reasoning over Dependencies Extracted Online. In Proceedings of the 4th Web as Corpus Workshop, pages 55–62, Marrakech, Morocco. European Language Resources Association.
Cite (Informal):
RoDEO: Reasoning over Dependencies Extracted Online (Siblini & Kosseim, WAC 2008)
Copy Citation:
PDF:
https://preview.aclanthology.org/jlcl-multiple-ingestion/2008.wac-1.9.pdf