Difference between revisions of "Eve: Explainable Vector based Embedding Technique Using Wikipedia"
(New work - Eve: Explainable Vector based Embedding Technique Using Wikipedia) |
(+ wikilinks) |
||
| Line 1: | Line 1: | ||
| − | '''Eve: Explainable Vector based Embedding Technique Using Wikipedia''' - scientific work related to Wikipedia quality published in 2018, written by M. Atif Qureshi and Derek Greene. | + | '''Eve: Explainable Vector based Embedding Technique Using Wikipedia''' - scientific work related to [[Wikipedia quality]] published in 2018, written by [[M. Atif Qureshi]] and [[Derek Greene]]. |
== Overview == | == Overview == | ||
| − | Authors present an unsupervised explainable vector embedding technique, called EVE, which is built upon the structure of Wikipedia. The proposed model defines the dimensions of a semantic vector representing a concept using human-readable labels, thereby it is readily interpretable. Specifically, each vector is constructed using the Wikipedia category graph structure together with the Wikipedia article link structure. To test the effectiveness of the proposed model, authors consider its usefulness in three fundamental tasks: 1) intruder detection—to evaluate its ability to identify a non-coherent vector from a list of coherent vectors, 2) ability to cluster—to evaluate its tendency to group related vectors together while keeping unrelated vectors in separate clusters, and 3) sorting relevant items first—to evaluate its ability to rank vectors (items) relevant to the query in the top order of the result. For each task, authors also propose a strategy to generate a task-specific human-interpretable explanation from the model. These demonstrate the overall effectiveness of the explainable embeddings generated by EVE. Finally, authors compare EVE with the Word2Vec, FastText, and GloVe embedding techniques across the three tasks, and report improvements over the state-of-the-art. | + | Authors present an unsupervised explainable vector embedding technique, called EVE, which is built upon the structure of [[Wikipedia]]. The proposed model defines the dimensions of a semantic vector representing a concept using human-readable labels, thereby it is readily interpretable. Specifically, each vector is constructed using the Wikipedia category graph structure together with the Wikipedia article link structure. To test the effectiveness of the proposed model, authors consider its usefulness in three fundamental tasks: 1) intruder detection—to evaluate its ability to identify a non-coherent vector from a list of coherent vectors, 2) ability to cluster—to evaluate its tendency to group related vectors together while keeping unrelated vectors in separate clusters, and 3) sorting relevant items first—to evaluate its ability to rank vectors (items) relevant to the query in the top order of the result. For each task, authors also propose a strategy to generate a task-specific human-interpretable explanation from the model. These demonstrate the overall effectiveness of the explainable embeddings generated by EVE. Finally, authors compare EVE with the Word2Vec, FastText, and GloVe embedding techniques across the three tasks, and report improvements over the state-of-the-art. |
Revision as of 11:38, 16 June 2019
Eve: Explainable Vector based Embedding Technique Using Wikipedia - scientific work related to Wikipedia quality published in 2018, written by M. Atif Qureshi and Derek Greene.
Overview
Authors present an unsupervised explainable vector embedding technique, called EVE, which is built upon the structure of Wikipedia. The proposed model defines the dimensions of a semantic vector representing a concept using human-readable labels, thereby it is readily interpretable. Specifically, each vector is constructed using the Wikipedia category graph structure together with the Wikipedia article link structure. To test the effectiveness of the proposed model, authors consider its usefulness in three fundamental tasks: 1) intruder detection—to evaluate its ability to identify a non-coherent vector from a list of coherent vectors, 2) ability to cluster—to evaluate its tendency to group related vectors together while keeping unrelated vectors in separate clusters, and 3) sorting relevant items first—to evaluate its ability to rank vectors (items) relevant to the query in the top order of the result. For each task, authors also propose a strategy to generate a task-specific human-interpretable explanation from the model. These demonstrate the overall effectiveness of the explainable embeddings generated by EVE. Finally, authors compare EVE with the Word2Vec, FastText, and GloVe embedding techniques across the three tasks, and report improvements over the state-of-the-art.
