Difference between revisions of "The People's Web Meets Linguistic Knowledge: Automatic Sense Alignment of Wikipedia and Wordnet"
(Links) |
(+ Infobox work) |
||
Line 1: | Line 1: | ||
+ | {{Infobox work | ||
+ | | title = The People's Web Meets Linguistic Knowledge: Automatic Sense Alignment of Wikipedia and Wordnet | ||
+ | | date = 2011 | ||
+ | | authors = [[Elisabeth Niemann]]<br />[[Iryna Gurevych]] | ||
+ | | link = https://dl.acm.org/citation.cfm?id=2002691 | ||
+ | }} | ||
'''The People's Web Meets Linguistic Knowledge: Automatic Sense Alignment of Wikipedia and Wordnet''' - scientific work related to [[Wikipedia quality]] published in 2011, written by [[Elisabeth Niemann]] and [[Iryna Gurevych]]. | '''The People's Web Meets Linguistic Knowledge: Automatic Sense Alignment of Wikipedia and Wordnet''' - scientific work related to [[Wikipedia quality]] published in 2011, written by [[Elisabeth Niemann]] and [[Iryna Gurevych]]. | ||
== Overview == | == Overview == | ||
Authors propose a method to automatically align [[WordNet]] synsets and [[Wikipedia]] articles to obtain a sense inventory of higher coverage and quality. For each WordNet synset, authors first extract a set of Wikipedia articles as alignment candidates; in a second step, authors determine which article (if any) is a valid alignment, i.e. is about the same sense or concept. In this paper, authors go significantly beyond state-of-the-art word overlap approaches, and apply a threshold-based Personalized PageRank method for the disambiguation step. Authors show that WordNet synsets can be aligned to Wikipedia articles with a performance of up to 0.78 F1-Measure based on a comprehensive, well-balanced reference dataset consisting of 1,815 manually annotated sense alignment candidates. The fully-aligned resource as well as the reference dataset is publicly available. | Authors propose a method to automatically align [[WordNet]] synsets and [[Wikipedia]] articles to obtain a sense inventory of higher coverage and quality. For each WordNet synset, authors first extract a set of Wikipedia articles as alignment candidates; in a second step, authors determine which article (if any) is a valid alignment, i.e. is about the same sense or concept. In this paper, authors go significantly beyond state-of-the-art word overlap approaches, and apply a threshold-based Personalized PageRank method for the disambiguation step. Authors show that WordNet synsets can be aligned to Wikipedia articles with a performance of up to 0.78 F1-Measure based on a comprehensive, well-balanced reference dataset consisting of 1,815 manually annotated sense alignment candidates. The fully-aligned resource as well as the reference dataset is publicly available. |
Revision as of 10:04, 30 August 2020
Authors | Elisabeth Niemann Iryna Gurevych |
---|---|
Publication date | 2011 |
Links | Original |
The People's Web Meets Linguistic Knowledge: Automatic Sense Alignment of Wikipedia and Wordnet - scientific work related to Wikipedia quality published in 2011, written by Elisabeth Niemann and Iryna Gurevych.
Overview
Authors propose a method to automatically align WordNet synsets and Wikipedia articles to obtain a sense inventory of higher coverage and quality. For each WordNet synset, authors first extract a set of Wikipedia articles as alignment candidates; in a second step, authors determine which article (if any) is a valid alignment, i.e. is about the same sense or concept. In this paper, authors go significantly beyond state-of-the-art word overlap approaches, and apply a threshold-based Personalized PageRank method for the disambiguation step. Authors show that WordNet synsets can be aligned to Wikipedia articles with a performance of up to 0.78 F1-Measure based on a comprehensive, well-balanced reference dataset consisting of 1,815 manually annotated sense alignment candidates. The fully-aligned resource as well as the reference dataset is publicly available.