000192707 001__ 192707
000192707 005__ 20190316235805.0
000192707 022__ $$a0004-3702
000192707 0247_ $$2doi$$a10.1016/j.artint.2012.06.004
000192707 037__ $$aARTICLE
000192707 245__ $$aComputing text semantic relatedness using the contents and links of a hypertext encyclopedia
000192707 269__ $$a2013
000192707 260__ $$bElsevier Science Bv$$c2013$$aAmsterdam
000192707 300__ $$a27
000192707 336__ $$aJournal Articles
000192707 520__ $$aWe propose a method for computing semantic relatedness between words or texts by using knowledge from hypertext encyclopedias such as Wikipedia. A network of concepts is built by filtering the encyclopedia's articles, each concept corresponding to an article. Two types of weighted links between concepts are considered: one based on hyperlinks between the texts of the articles, and another one based on the lexical similarity between them. We propose and implement an efficient random walk algorithm that computes the distance between nodes, and then between sets of nodes, using the visiting probability from one (set of) node(s) to another. Moreover, to make the algorithm tractable, we propose and validate empirically two truncation methods, and then use an embedding space to learn an approximation of visiting probability. To evaluate the proposed distance, we apply our method to four important tasks in natural language processing: word similarity, document similarity, document clustering and classification, and ranking in information retrieval. The performance of the method is state-of-the-art or close to it for each task, thus demonstrating the generality of the knowledge resource. Moreover, using both hyperlinks and lexical similarity links improves the scores with respect to a method using only one of them, because hyperlinks bring additional real-world knowledge not captured by lexical similarity. (C) 2012 Elsevier B.V. All rights reserved.
000192707 6531_ $$aText semantic relatedness
000192707 6531_ $$aDistance metric learning
000192707 6531_ $$aLearning to rank
000192707 6531_ $$aRandom walk
000192707 6531_ $$aText classification
000192707 6531_ $$aText similarity
000192707 6531_ $$aDocument clustering
000192707 6531_ $$aInformation retrieval
000192707 6531_ $$aWord similarity
000192707 700__ $$0246033$$g183770$$uIdiap Res Inst, CH-1920 Martigny, Switzerland$$aYazdani, Majid
000192707 700__ $$aPopescu-Belis, Andrei$$uIdiap Res Inst, CH-1920 Martigny, Switzerland
000192707 773__ $$j194$$tArtificial Intelligence$$q176-202
000192707 8564_ $$uhttps://infoscience.epfl.ch/record/192707/files/Yazdani_AIJ_2012.pdf$$zn/a$$s354703$$yn/a
000192707 909C0 $$xU10381$$0252189$$pLIDIAP
000192707 909CO $$ooai:infoscience.tind.io:192707$$qGLOBAL_SET$$pSTI$$particle
000192707 937__ $$aEPFL-ARTICLE-192707
000192707 973__ $$rREVIEWED$$sPUBLISHED$$aEPFL
000192707 970__ $$aYazdani_AIJ_2012/LIDIAP
000192707 980__ $$aARTICLE