Semantic annotation with RescoredESA: Rescoring concept features generated from explicit semantic analysis. Jiang, Z., Chen, M., & Liu, X. In ESAIR 2014 - Proceedings of the 7th International Workshop on Exploiting Semantic Annotations in Information Retrieval, co-located with CIKM 2014, 2014. doi abstract bibtex Copyright 2014 ACM. Concepts have been used extensively in semantic annotating. Explicit Semantic Analysis (ESA) is a concept feature generator, which represents text by a concept-level vector, such as a vector of Wikipedia concepts [3, 4, 8] . It is also considered a human-friendly way to annotate text - it generates concept vector that can be easily interpreted by human. We propose an approach, RescoredESA, based on ESA, according to aspects upon which ESA can enhance: 1) sometimes the output vectors do not assign high scores to concepts relevant to the text; 2) it considers words in the text when representing the text to concept-level vector while not considering the concepts explicitly occurring in the text, which can be an important source for assigning scores to ESA vector dimensions. We evaluate it against the 20 newsgroup classification task, and the result shows a slight enhancement when combining vectors from RescoredESA and bag-of-words.
@inproceedings{
title = {Semantic annotation with RescoredESA: Rescoring concept features generated from explicit semantic analysis},
type = {inproceedings},
year = {2014},
id = {b267dedb-f9a4-3e34-85c9-0358b883658f},
created = {2019-10-01T17:20:59.889Z},
file_attached = {false},
profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d},
last_modified = {2019-10-01T17:23:48.872Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {Jiang2014},
folder_uuids = {73f994b4-a3be-4035-a6dd-3802077ce863},
private_publication = {false},
abstract = {Copyright 2014 ACM. Concepts have been used extensively in semantic annotating. Explicit Semantic Analysis (ESA) is a concept feature generator, which represents text by a concept-level vector, such as a vector of Wikipedia concepts [3, 4, 8] . It is also considered a human-friendly way to annotate text - it generates concept vector that can be easily interpreted by human. We propose an approach, RescoredESA, based on ESA, according to aspects upon which ESA can enhance: 1) sometimes the output vectors do not assign high scores to concepts relevant to the text; 2) it considers words in the text when representing the text to concept-level vector while not considering the concepts explicitly occurring in the text, which can be an important source for assigning scores to ESA vector dimensions. We evaluate it against the 20 newsgroup classification task, and the result shows a slight enhancement when combining vectors from RescoredESA and bag-of-words.},
bibtype = {inproceedings},
author = {Jiang, Z. and Chen, M. and Liu, X.},
doi = {10.1145/2663712.2666192},
booktitle = {ESAIR 2014 - Proceedings of the 7th International Workshop on Exploiting Semantic Annotations in Information Retrieval, co-located with CIKM 2014}
}
Downloads: 0
{"_id":"GnsMABJvZhRqxnwLY","bibbaseid":"jiang-chen-liu-semanticannotationwithrescoredesarescoringconceptfeaturesgeneratedfromexplicitsemanticanalysis-2014","downloads":0,"creationDate":"2018-03-12T19:10:27.510Z","title":"Semantic annotation with RescoredESA: Rescoring concept features generated from explicit semantic analysis","author_short":["Jiang, Z.","Chen, M.","Liu, X."],"year":2014,"bibtype":"inproceedings","biburl":"https://bibbase.org/service/mendeley/42d295c0-0737-38d6-8b43-508cab6ea85d","bibdata":{"title":"Semantic annotation with RescoredESA: Rescoring concept features generated from explicit semantic analysis","type":"inproceedings","year":"2014","id":"b267dedb-f9a4-3e34-85c9-0358b883658f","created":"2019-10-01T17:20:59.889Z","file_attached":false,"profile_id":"42d295c0-0737-38d6-8b43-508cab6ea85d","last_modified":"2019-10-01T17:23:48.872Z","read":false,"starred":false,"authored":"true","confirmed":"true","hidden":false,"citation_key":"Jiang2014","folder_uuids":"73f994b4-a3be-4035-a6dd-3802077ce863","private_publication":false,"abstract":"Copyright 2014 ACM. Concepts have been used extensively in semantic annotating. Explicit Semantic Analysis (ESA) is a concept feature generator, which represents text by a concept-level vector, such as a vector of Wikipedia concepts [3, 4, 8] . It is also considered a human-friendly way to annotate text - it generates concept vector that can be easily interpreted by human. We propose an approach, RescoredESA, based on ESA, according to aspects upon which ESA can enhance: 1) sometimes the output vectors do not assign high scores to concepts relevant to the text; 2) it considers words in the text when representing the text to concept-level vector while not considering the concepts explicitly occurring in the text, which can be an important source for assigning scores to ESA vector dimensions. We evaluate it against the 20 newsgroup classification task, and the result shows a slight enhancement when combining vectors from RescoredESA and bag-of-words.","bibtype":"inproceedings","author":"Jiang, Z. and Chen, M. and Liu, X.","doi":"10.1145/2663712.2666192","booktitle":"ESAIR 2014 - Proceedings of the 7th International Workshop on Exploiting Semantic Annotations in Information Retrieval, co-located with CIKM 2014","bibtex":"@inproceedings{\n title = {Semantic annotation with RescoredESA: Rescoring concept features generated from explicit semantic analysis},\n type = {inproceedings},\n year = {2014},\n id = {b267dedb-f9a4-3e34-85c9-0358b883658f},\n created = {2019-10-01T17:20:59.889Z},\n file_attached = {false},\n profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d},\n last_modified = {2019-10-01T17:23:48.872Z},\n read = {false},\n starred = {false},\n authored = {true},\n confirmed = {true},\n hidden = {false},\n citation_key = {Jiang2014},\n folder_uuids = {73f994b4-a3be-4035-a6dd-3802077ce863},\n private_publication = {false},\n abstract = {Copyright 2014 ACM. Concepts have been used extensively in semantic annotating. Explicit Semantic Analysis (ESA) is a concept feature generator, which represents text by a concept-level vector, such as a vector of Wikipedia concepts [3, 4, 8] . It is also considered a human-friendly way to annotate text - it generates concept vector that can be easily interpreted by human. We propose an approach, RescoredESA, based on ESA, according to aspects upon which ESA can enhance: 1) sometimes the output vectors do not assign high scores to concepts relevant to the text; 2) it considers words in the text when representing the text to concept-level vector while not considering the concepts explicitly occurring in the text, which can be an important source for assigning scores to ESA vector dimensions. We evaluate it against the 20 newsgroup classification task, and the result shows a slight enhancement when combining vectors from RescoredESA and bag-of-words.},\n bibtype = {inproceedings},\n author = {Jiang, Z. and Chen, M. and Liu, X.},\n doi = {10.1145/2663712.2666192},\n booktitle = {ESAIR 2014 - Proceedings of the 7th International Workshop on Exploiting Semantic Annotations in Information Retrieval, co-located with CIKM 2014}\n}","author_short":["Jiang, Z.","Chen, M.","Liu, X."],"biburl":"https://bibbase.org/service/mendeley/42d295c0-0737-38d6-8b43-508cab6ea85d","bibbaseid":"jiang-chen-liu-semanticannotationwithrescoredesarescoringconceptfeaturesgeneratedfromexplicitsemanticanalysis-2014","role":"author","urls":{},"metadata":{"authorlinks":{}},"downloads":0},"search_terms":["semantic","annotation","rescoredesa","rescoring","concept","features","generated","explicit","semantic","analysis","jiang","chen","liu"],"keywords":[],"authorIDs":[],"dataSources":["zgahneP4uAjKbudrQ","ya2CyA73rpZseyrZ8","2252seNhipfTmjEBQ"]}