Volltext-Downloads (blau) und Frontdoor-Views (grau)

Learning thesaurus relations from distributional features

  • In distributional semantics words are represented by aggregated context features. The similarity of words can be computed by comparing their feature vectors. Thus, we can predict whether two words are synonymous or similar with respect to some other semantic relation. We will show on six different datasets of pairs of similar and non-similar words that a supervised learning algorithm on feature vectors representing pairs of words outperforms cosine similarity between vectors representing single words. We compared different methods to construct a feature vector representing a pair of words. We show that simple methods like pairwise addition or multiplication give better results than a recently proposed method that combines different types of features. The semantic relation we consider is relatedness of terms in thesauri for intellectual document classification. Thus our findings can directly be applied for the maintenance and extension of such thesauri. To the best of our knowledge this relation was not considered before in the field of distributional semantics.

Download full text files

Export metadata

Additional Services

Search Google Scholar


Author:Rosa Tsegaye Aga, Christian WartenaORCiDGND, Lucas Drumond, Lars Schmidt-Thieme
Parent Title (English):LREC 2016, Tenth International Conference on Language Resources and Evaluation
Document Type:Conference Proceeding
Year of Completion:2016
Publishing Institution:Hochschule Hannover
Release Date:2017/06/27
Tag:context vectors; distributional semantics; supervised machine learning; thesauri
GND Keyword:Thesaurus; Überwachtes Lernen; Semantik
First Page:2071
Last Page:2075
Link to catalogue:1014113253
Institutes:Fakultät III - Medien, Information und Design
DDC classes:020 Bibliotheks- und Informationswissenschaft
Licence (German):License LogoCreative Commons - CC BY-NC - Namensnennung - Nicht kommerziell 4.0 International