Difference between revisions of "A Named Entity Labeler for German: Exploiting Wikipedia and Distributional Clusters"
(Adding wikilinks) |
(infobox) |
||
| Line 1: | Line 1: | ||
| + | {{Infobox work | ||
| + | | title = A Named Entity Labeler for German: Exploiting Wikipedia and Distributional Clusters | ||
| + | | date = 2010 | ||
| + | | authors = [[Grzegorz Chrupała]]<br />[[Dietrich Klakow]] | ||
| + | | link = http://www.lrec-conf.org/proceedings/lrec2010/pdf/538_Paper.pdf | ||
| + | }} | ||
'''A Named Entity Labeler for German: Exploiting Wikipedia and Distributional Clusters''' - scientific work related to [[Wikipedia quality]] published in 2010, written by [[Grzegorz Chrupała]] and [[Dietrich Klakow]]. | '''A Named Entity Labeler for German: Exploiting Wikipedia and Distributional Clusters''' - scientific work related to [[Wikipedia quality]] published in 2010, written by [[Grzegorz Chrupała]] and [[Dietrich Klakow]]. | ||
== Overview == | == Overview == | ||
Named Entity Recognition is a relatively well-understood NLP task, with many publicly available training resources and software for English. Other languages tend to be underserved in this area. For German, CoNLL-2003 provides training data, but there are no publicly available, ready-to-use tools. Authors fill this gap and develop a German NER system with state-of-the-art performance. In addition to CoNLL 2003 labeled training data, authors use two additional resources: (i) 32 million words of unlabeled text and (ii) infobox labels in German [[Wikipedia]] articles. Authors extract informative [[features]] of word-types from those resources and train a supervised model on the labeled training data. This approach allows us to deal better with word-types unseen in the training data and achieve state-of-the-art performance on German with little engineering effort. | Named Entity Recognition is a relatively well-understood NLP task, with many publicly available training resources and software for English. Other languages tend to be underserved in this area. For German, CoNLL-2003 provides training data, but there are no publicly available, ready-to-use tools. Authors fill this gap and develop a German NER system with state-of-the-art performance. In addition to CoNLL 2003 labeled training data, authors use two additional resources: (i) 32 million words of unlabeled text and (ii) infobox labels in German [[Wikipedia]] articles. Authors extract informative [[features]] of word-types from those resources and train a supervised model on the labeled training data. This approach allows us to deal better with word-types unseen in the training data and achieve state-of-the-art performance on German with little engineering effort. | ||
Revision as of 07:26, 16 January 2021
Authors | Grzegorz Chrupała Dietrich Klakow |
|---|---|
Publication date | 2010 |
Links | Original |
A Named Entity Labeler for German: Exploiting Wikipedia and Distributional Clusters - scientific work related to Wikipedia quality published in 2010, written by Grzegorz Chrupała and Dietrich Klakow.
Overview
Named Entity Recognition is a relatively well-understood NLP task, with many publicly available training resources and software for English. Other languages tend to be underserved in this area. For German, CoNLL-2003 provides training data, but there are no publicly available, ready-to-use tools. Authors fill this gap and develop a German NER system with state-of-the-art performance. In addition to CoNLL 2003 labeled training data, authors use two additional resources: (i) 32 million words of unlabeled text and (ii) infobox labels in German Wikipedia articles. Authors extract informative features of word-types from those resources and train a supervised model on the labeled training data. This approach allows us to deal better with word-types unseen in the training data and achieve state-of-the-art performance on German with little engineering effort.
