There has recently been an increased interest in named entity recognition and disambiguation systems at major conferences such as WWW, SIGIR, ACL, KDD, etc. However, most work has focused on algorithms and evaluations, leaving little space for implementation details. In this paper, we discuss some implementation and data processing challenges we encountered while developing a new multilingual version of DBpedia Spotlight that is faster, more accurate and easier to configure. We compare our solution to the previous system, considering time performance, space requirements and accuracy in the context of the Dutch and English languages. Additionally, we report results for 9 additional languages among the largest Wikipedias. Finally, we present challenges and experiences to foment the discussion with other developers interested in recognition and disambiguation of entities in natural language text.
Description
Improving efficiency and accuracy in multilingual entity extraction
%0 Conference Paper
%1 Daiber2013
%A Daiber, Joachim
%A Jakob, Max
%A Hokamp, Chris
%A Mendes, Pablo N.
%B Proceedings of the 9th International Conference on Semantic Systems
%C New York, NY, USA
%D 2013
%I ACM
%K dbpedia keyword_extraction wikipedia
%P 121--124
%R 10.1145/2506182.2506198
%T Improving efficiency and accuracy in multilingual entity extraction
%U http://doi.acm.org/10.1145/2506182.2506198
%X There has recently been an increased interest in named entity recognition and disambiguation systems at major conferences such as WWW, SIGIR, ACL, KDD, etc. However, most work has focused on algorithms and evaluations, leaving little space for implementation details. In this paper, we discuss some implementation and data processing challenges we encountered while developing a new multilingual version of DBpedia Spotlight that is faster, more accurate and easier to configure. We compare our solution to the previous system, considering time performance, space requirements and accuracy in the context of the Dutch and English languages. Additionally, we report results for 9 additional languages among the largest Wikipedias. Finally, we present challenges and experiences to foment the discussion with other developers interested in recognition and disambiguation of entities in natural language text.
%@ 978-1-4503-1972-0
@inproceedings{Daiber2013,
abstract = {There has recently been an increased interest in named entity recognition and disambiguation systems at major conferences such as WWW, SIGIR, ACL, KDD, etc. However, most work has focused on algorithms and evaluations, leaving little space for implementation details. In this paper, we discuss some implementation and data processing challenges we encountered while developing a new multilingual version of DBpedia Spotlight that is faster, more accurate and easier to configure. We compare our solution to the previous system, considering time performance, space requirements and accuracy in the context of the Dutch and English languages. Additionally, we report results for 9 additional languages among the largest Wikipedias. Finally, we present challenges and experiences to foment the discussion with other developers interested in recognition and disambiguation of entities in natural language text.},
acmid = {2506198},
added-at = {2013-10-14T16:07:20.000+0200},
address = {New York, NY, USA},
author = {Daiber, Joachim and Jakob, Max and Hokamp, Chris and Mendes, Pablo N.},
biburl = {https://www.bibsonomy.org/bibtex/28015725b6b8c186ad89fb925f6c0cc7a/lopusz_kdd},
booktitle = {Proceedings of the 9th International Conference on Semantic Systems},
description = {Improving efficiency and accuracy in multilingual entity extraction},
doi = {10.1145/2506182.2506198},
interhash = {a7b34b19bff15f95c42a578c56625e95},
intrahash = {8015725b6b8c186ad89fb925f6c0cc7a},
isbn = {978-1-4503-1972-0},
keywords = {dbpedia keyword_extraction wikipedia},
location = {Graz, Austria},
numpages = {4},
pages = {121--124},
publisher = {ACM},
series = {I-SEMANTICS '13},
timestamp = {2013-10-14T16:11:37.000+0200},
title = {Improving efficiency and accuracy in multilingual entity extraction},
url = {http://doi.acm.org/10.1145/2506182.2506198},
year = 2013
}