Difference between revisions of "Using Wikipedia for Cross-Language Named Entity Recognition"
(+ category) |
(cats.) |
||
(One intermediate revision by one other user not shown) | |||
Line 1: | Line 1: | ||
{{Infobox work | {{Infobox work | ||
| title = Using Wikipedia for Cross-Language Named Entity Recognition | | title = Using Wikipedia for Cross-Language Named Entity Recognition | ||
− | | date = | + | | date = 2016 |
− | | authors = [[Eraldo R. Fernandes]]<br />[[Ulf Brefeld]]<br />[[ | + | | authors = [[Eraldo R. Fernandes]]<br />[[Ulf Brefeld]]<br />[[R Blanco Gonzalez]]<br />[[J Asterias]] |
− | + | | link = https://researchbank.rmit.edu.au/view/rmit:44541 | |
− | | link = https:// | ||
}} | }} | ||
− | '''Using Wikipedia for Cross-Language Named Entity Recognition''' - scientific work related to [[Wikipedia quality]] published in | + | '''Using Wikipedia for Cross-Language Named Entity Recognition''' - scientific work related to [[Wikipedia quality]] published in 2016, written by [[Eraldo R. Fernandes]], [[Ulf Brefeld]], [[R Blanco Gonzalez]] and [[J Asterias]]. |
== Overview == | == Overview == | ||
− | Named [[entity recognition]] and classification NERC is fundamental for [[natural language processing]] tasks such as [[information extraction]], [[question answering]], and topic detection. State-of-the-art NERC systems are based on supervised machine learning and hence need to be trained on manually annotated corpora. However, annotated corpora hardly exist for non-standard languages and labeling additional data manually is tedious and costly. In this article, authors present a novel method to automatically generate partially annotated corpora for NERC by exploiting the link structure of [[Wikipedia]]. Firstly, Wikipedia entries in the source language are labeled with the NERC tag set. Secondly, Wikipedia language links are exploited to propagate the annotations in the target language. Finally, mentions of the labeled entities in the target language are annotated with the respective tags. The procedure results in a partially annotated corpus that is likely to contain unannotated entities. To learn from such partially annotated data, authors devise two simple extensions of hidden Markov models and structural perceptrons. Empirically, authors observe that using the automatically generated data leads to more accurate prediction models than off-the-shelf NERC methods. Authors demonstrate that the novel extensions of HMMs and perceptrons effectively exploit the partially annotated data and outperforms their baseline counterparts in all settings. | + | Named [[entity recognition]] and classification (NERC) is fundamental for [[natural language processing]] tasks such as [[information extraction]], [[question answering]], and topic detection. State-of-the-art NERC systems are based on supervised machine learning and hence need to be trained on (manually) annotated corpora. However, annotated corpora hardly exist for non-standard languages and labeling additional data manually is tedious and costly. In this article, authors present a novel method to automatically generate (partially) annotated corpora for NERC by exploiting the link structure of [[Wikipedia]]. Firstly, Wikipedia entries in the source language are labeled with the NERC tag set. Secondly, Wikipedia language links are exploited to propagate the annotations in the target language. Finally, mentions of the labeled entities in the target language are annotated with the respective tags. The procedure results in a partially annotated corpus that is likely to contain unannotated entities. To learn from such partially annotated data, authors devise two simple extensions of hidden Markov models and structural perceptrons. Empirically, authors observe that using the automatically generated data leads to more accurate prediction models than off-the-shelf NERC methods. Authors demonstrate that the novel extensions of HMMs and perceptrons effectively exploit the partially annotated data and outperforms their baseline counterparts in all settings. |
== Embed == | == Embed == | ||
Line 15: | Line 14: | ||
<code> | <code> | ||
<nowiki> | <nowiki> | ||
− | Fernandes, Eraldo R.; Brefeld, Ulf; Blanco | + | Fernandes, Eraldo R.; Brefeld, Ulf; Gonzalez, R Blanco; Asterias, J. (2016). "[[Using Wikipedia for Cross-Language Named Entity Recognition]]". Springer. |
</nowiki> | </nowiki> | ||
</code> | </code> | ||
Line 22: | Line 21: | ||
<code> | <code> | ||
<nowiki> | <nowiki> | ||
− | {{cite journal |last1=Fernandes |first1=Eraldo R. |last2=Brefeld |first2=Ulf |last3= | + | {{cite journal |last1=Fernandes |first1=Eraldo R. |last2=Brefeld |first2=Ulf |last3=Gonzalez |first3=R Blanco |last4=Asterias |first4=J |title=Using Wikipedia for Cross-Language Named Entity Recognition |date=2016 |url=https://wikipediaquality.com/wiki/Using_Wikipedia_for_Cross-Language_Named_Entity_Recognition |journal=Springer}} |
</nowiki> | </nowiki> | ||
</code> | </code> | ||
Line 29: | Line 28: | ||
<code> | <code> | ||
<nowiki> | <nowiki> | ||
− | Fernandes, Eraldo R.; Brefeld, Ulf; Blanco | + | Fernandes, Eraldo R.; Brefeld, Ulf; Gonzalez, R Blanco; Asterias, J. (2016). &quot;<a href="https://wikipediaquality.com/wiki/Using_Wikipedia_for_Cross-Language_Named_Entity_Recognition">Using Wikipedia for Cross-Language Named Entity Recognition</a>&quot;. Springer. |
</nowiki> | </nowiki> | ||
</code> | </code> |
Latest revision as of 15:08, 17 November 2020
Authors | Eraldo R. Fernandes Ulf Brefeld R Blanco Gonzalez J Asterias |
---|---|
Publication date | 2016 |
Links | Original |
Using Wikipedia for Cross-Language Named Entity Recognition - scientific work related to Wikipedia quality published in 2016, written by Eraldo R. Fernandes, Ulf Brefeld, R Blanco Gonzalez and J Asterias.
Overview
Named entity recognition and classification (NERC) is fundamental for natural language processing tasks such as information extraction, question answering, and topic detection. State-of-the-art NERC systems are based on supervised machine learning and hence need to be trained on (manually) annotated corpora. However, annotated corpora hardly exist for non-standard languages and labeling additional data manually is tedious and costly. In this article, authors present a novel method to automatically generate (partially) annotated corpora for NERC by exploiting the link structure of Wikipedia. Firstly, Wikipedia entries in the source language are labeled with the NERC tag set. Secondly, Wikipedia language links are exploited to propagate the annotations in the target language. Finally, mentions of the labeled entities in the target language are annotated with the respective tags. The procedure results in a partially annotated corpus that is likely to contain unannotated entities. To learn from such partially annotated data, authors devise two simple extensions of hidden Markov models and structural perceptrons. Empirically, authors observe that using the automatically generated data leads to more accurate prediction models than off-the-shelf NERC methods. Authors demonstrate that the novel extensions of HMMs and perceptrons effectively exploit the partially annotated data and outperforms their baseline counterparts in all settings.
Embed
Wikipedia Quality
Fernandes, Eraldo R.; Brefeld, Ulf; Gonzalez, R Blanco; Asterias, J. (2016). "[[Using Wikipedia for Cross-Language Named Entity Recognition]]". Springer.
English Wikipedia
{{cite journal |last1=Fernandes |first1=Eraldo R. |last2=Brefeld |first2=Ulf |last3=Gonzalez |first3=R Blanco |last4=Asterias |first4=J |title=Using Wikipedia for Cross-Language Named Entity Recognition |date=2016 |url=https://wikipediaquality.com/wiki/Using_Wikipedia_for_Cross-Language_Named_Entity_Recognition |journal=Springer}}
HTML
Fernandes, Eraldo R.; Brefeld, Ulf; Gonzalez, R Blanco; Asterias, J. (2016). "<a href="https://wikipediaquality.com/wiki/Using_Wikipedia_for_Cross-Language_Named_Entity_Recognition">Using Wikipedia for Cross-Language Named Entity Recognition</a>". Springer.