Combining heterogeneous knowledge resources for improved distributional semantic models (bibtex)
by György Szarvas, Torsten Zesch and Iryna Gurevych
Abstract:
The Explicit Semantic Analysis (ESA) model based on term cooccurrences in Wikipedia has been regarded as state-of-the-art semantic relatedness measure in the recent years. We provide an analysis of the important parameters of ESA using datasets in five different languages. Additionally, we propose the use of ESA with multiple lexical semantic resources thus exploiting multiple evidence of term cooccurrence to improve over the Wikipedia-based measure. Exploiting the improved robustness and coverage of the proposed combination, we report improved performance over single resources in word semantic relatedness, solving word choice problems, classification of semantic relations between nominals, and text similarity.
Reference:
Combining heterogeneous knowledge resources for improved distributional semantic models György Szarvas, Torsten Zesch and Iryna Gurevych, Chapter in Proceedings of the 12th International Conference on Intelligent Text Processing and Computational Linguistics (Alexander Gelbukh, ed.), Springer, volume 6608, 2011.
Bibtex Entry:
@incollection{TUD-CS-2011-0069b,
abstract = {The Explicit Semantic Analysis (ESA) model based on term cooccurrences in Wikipedia has been regarded as state-of-the-art semantic relatedness measure in the recent years. We provide an analysis of the important parameters of ESA using datasets in five different languages. Additionally, we propose the use of ESA with multiple lexical semantic resources thus exploiting multiple evidence of term cooccurrence to improve over the Wikipedia-based measure. Exploiting the improved robustness and coverage of the proposed combination, we report improved performance over single resources in word semantic relatedness, solving word choice problems, classification of semantic relations between nominals, and text similarity.},
address = {Berlin/Heidelberg, Germany},
author = {Szarvas, Gy{\"{o}}rgy and Zesch, Torsten and Gurevych, Iryna},
booktitle = {Proceedings of the 12th International Conference on Intelligent Text Processing and Computational Linguistics},
editor = {Gelbukh, Alexander},
pages = {289--303},
publisher = {Springer},
series = {Lecture Notes in Computer Science},
title = {{Combining heterogeneous knowledge resources for improved distributional semantic models}},
url = {https://link.springer.com/chapter/10.1007/978-3-642-19400-9_23},
volume = {6608},
year = {2011}
}