Difference between revisions of "Sequential Supervised Learning for Hypernym Discovery from Wikipedia"
(infobox) |
(Embed) |
||
| Line 10: | Line 10: | ||
== Overview == | == Overview == | ||
Hypernym discovery is an essential task for building and extending ontologies automatically. In comparison to the whole Web as a source for [[information extraction]], online encyclopedias provide far more structuredness and [[reliability]]. In this paper authors propose a novel approach that combines syntactic and lexical-[[semantic information]] to identify hypernymic relationships. Authors compiled semi-automatically and manually created training data and a gold standard for evaluation with the first sentences from the German version of [[Wikipedia]]. Authors trained a sequential supervised learner with a semantically enhanced tagset. The experiments showed that the cleanliness of the data is far more important than the amount of the same. Furthermore, it was shown that bootstrapping is a viable approach to ameliorate the results. Authors approach outperformed the competitive lexico-syntactic patterns by 7% leading to an F 1-measure of over .91. | Hypernym discovery is an essential task for building and extending ontologies automatically. In comparison to the whole Web as a source for [[information extraction]], online encyclopedias provide far more structuredness and [[reliability]]. In this paper authors propose a novel approach that combines syntactic and lexical-[[semantic information]] to identify hypernymic relationships. Authors compiled semi-automatically and manually created training data and a gold standard for evaluation with the first sentences from the German version of [[Wikipedia]]. Authors trained a sequential supervised learner with a semantically enhanced tagset. The experiments showed that the cleanliness of the data is far more important than the amount of the same. Furthermore, it was shown that bootstrapping is a viable approach to ameliorate the results. Authors approach outperformed the competitive lexico-syntactic patterns by 7% leading to an F 1-measure of over .91. | ||
| + | |||
| + | == Embed == | ||
| + | === Wikipedia Quality === | ||
| + | <code> | ||
| + | <nowiki> | ||
| + | Litz, Berenike; Langer, Hagen; Malaka, Rainer. (2009). "[[Sequential Supervised Learning for Hypernym Discovery from Wikipedia]]". Springer Berlin Heidelberg. DOI: 10.1007/978-3-642-19032-2_5. | ||
| + | </nowiki> | ||
| + | </code> | ||
| + | |||
| + | === English Wikipedia === | ||
| + | <code> | ||
| + | <nowiki> | ||
| + | {{cite journal |last1=Litz |first1=Berenike |last2=Langer |first2=Hagen |last3=Malaka |first3=Rainer |title=Sequential Supervised Learning for Hypernym Discovery from Wikipedia |date=2009 |doi=10.1007/978-3-642-19032-2_5 |url=https://wikipediaquality.com/wiki/Sequential_Supervised_Learning_for_Hypernym_Discovery_from_Wikipedia |journal=Springer Berlin Heidelberg}} | ||
| + | </nowiki> | ||
| + | </code> | ||
| + | |||
| + | === HTML === | ||
| + | <code> | ||
| + | <nowiki> | ||
| + | Litz, Berenike; Langer, Hagen; Malaka, Rainer. (2009). &quot;<a href="https://wikipediaquality.com/wiki/Sequential_Supervised_Learning_for_Hypernym_Discovery_from_Wikipedia">Sequential Supervised Learning for Hypernym Discovery from Wikipedia</a>&quot;. Springer Berlin Heidelberg. DOI: 10.1007/978-3-642-19032-2_5. | ||
| + | </nowiki> | ||
| + | </code> | ||
Revision as of 08:41, 6 January 2020
Authors | Berenike Litz Hagen Langer Rainer Malaka |
|---|---|
Publication date | 2009 |
DOI | 10.1007/978-3-642-19032-2_5 |
Links | Original |
Sequential Supervised Learning for Hypernym Discovery from Wikipedia - scientific work related to Wikipedia quality published in 2009, written by Berenike Litz, Hagen Langer and Rainer Malaka.
Overview
Hypernym discovery is an essential task for building and extending ontologies automatically. In comparison to the whole Web as a source for information extraction, online encyclopedias provide far more structuredness and reliability. In this paper authors propose a novel approach that combines syntactic and lexical-semantic information to identify hypernymic relationships. Authors compiled semi-automatically and manually created training data and a gold standard for evaluation with the first sentences from the German version of Wikipedia. Authors trained a sequential supervised learner with a semantically enhanced tagset. The experiments showed that the cleanliness of the data is far more important than the amount of the same. Furthermore, it was shown that bootstrapping is a viable approach to ameliorate the results. Authors approach outperformed the competitive lexico-syntactic patterns by 7% leading to an F 1-measure of over .91.
Embed
Wikipedia Quality
Litz, Berenike; Langer, Hagen; Malaka, Rainer. (2009). "[[Sequential Supervised Learning for Hypernym Discovery from Wikipedia]]". Springer Berlin Heidelberg. DOI: 10.1007/978-3-642-19032-2_5.
English Wikipedia
{{cite journal |last1=Litz |first1=Berenike |last2=Langer |first2=Hagen |last3=Malaka |first3=Rainer |title=Sequential Supervised Learning for Hypernym Discovery from Wikipedia |date=2009 |doi=10.1007/978-3-642-19032-2_5 |url=https://wikipediaquality.com/wiki/Sequential_Supervised_Learning_for_Hypernym_Discovery_from_Wikipedia |journal=Springer Berlin Heidelberg}}
HTML
Litz, Berenike; Langer, Hagen; Malaka, Rainer. (2009). "<a href="https://wikipediaquality.com/wiki/Sequential_Supervised_Learning_for_Hypernym_Discovery_from_Wikipedia">Sequential Supervised Learning for Hypernym Discovery from Wikipedia</a>". Springer Berlin Heidelberg. DOI: 10.1007/978-3-642-19032-2_5.
