Difference between revisions of "Fine-Grained Named Entity Classification with Wikipedia Article Vectors"
(New work - Fine-Grained Named Entity Classification with Wikipedia Article Vectors) |
(+ links) |
||
| Line 1: | Line 1: | ||
| − | '''Fine-Grained Named Entity Classification with Wikipedia Article Vectors''' - scientific work related to Wikipedia quality published in 2016, written by Masatoshi Suzuki, Koji Matsuda, Satoshi Sekine, Naoaki Okazaki and Kentaro Inui. | + | '''Fine-Grained Named Entity Classification with Wikipedia Article Vectors''' - scientific work related to [[Wikipedia quality]] published in 2016, written by [[Masatoshi Suzuki]], [[Koji Matsuda]], [[Satoshi Sekine]], [[Naoaki Okazaki]] and [[Kentaro Inui]]. |
== Overview == | == Overview == | ||
| − | This paper addresses the task of assigning multiple labels of fine-grained named entity (NE) types to Wikipedia articles. To address the sparseness of the input feature space, which is salient particularly in fine-grained type classification, authors propose to learn article vectors (i.e. entity embeddings) from hypertext structure of Wikipedia using a Skip-gram model and incorporate them into the input feature set. To conduct large-scale practical experiments, authors created a new dataset containing over 22,000 manually labeled instances. The results of experiments show that idea gained statistically significant improvements in classification results. | + | This paper addresses the task of assigning multiple labels of fine-grained [[named entity]] (NE) types to [[Wikipedia]] articles. To address the sparseness of the input feature space, which is salient particularly in fine-grained type classification, authors propose to learn article vectors (i.e. entity embeddings) from hypertext structure of Wikipedia using a Skip-gram model and incorporate them into the input feature set. To conduct large-scale practical experiments, authors created a new dataset containing over 22,000 manually labeled instances. The results of experiments show that idea gained statistically significant improvements in classification results. |
Revision as of 13:58, 21 December 2019
Fine-Grained Named Entity Classification with Wikipedia Article Vectors - scientific work related to Wikipedia quality published in 2016, written by Masatoshi Suzuki, Koji Matsuda, Satoshi Sekine, Naoaki Okazaki and Kentaro Inui.
Overview
This paper addresses the task of assigning multiple labels of fine-grained named entity (NE) types to Wikipedia articles. To address the sparseness of the input feature space, which is salient particularly in fine-grained type classification, authors propose to learn article vectors (i.e. entity embeddings) from hypertext structure of Wikipedia using a Skip-gram model and incorporate them into the input feature set. To conduct large-scale practical experiments, authors created a new dataset containing over 22,000 manually labeled instances. The results of experiments show that idea gained statistically significant improvements in classification results.
