Difference between revisions of "The People's Web Meets Linguistic Knowledge: Automatic Sense Alignment of Wikipedia and Wordnet"
(Starting an article - The People's Web Meets Linguistic Knowledge: Automatic Sense Alignment of Wikipedia and Wordnet) |
(Links) |
||
Line 1: | Line 1: | ||
− | '''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 08:26, 26 August 2020
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.