Automatically Creating Datasets for Measures of Semantic Relatedness

By Torsten Zesch, Iryna Gurevych. 2006

79 citations recorded by the source corpus.

Semantic relatedness is a special form of linguistic distance between words. Evaluating semantic relatedness measures is usually performed by comparison with human judgments. Previous test datasets had been created analytically and were limited in size. We propose a corpus-based system for automatically creating test datasets. Experiments with human subjects show that the resulting datasets cover all degrees of relatedness. As a result of the corpus-based approach, test datasets cover all types of lexical-semantic relations and contain domain-specific words naturally occurring in texts.

Subfields: Artificial Intelligence, Natural Language Processing, Evaluation & Benchmarks

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Natural Language Processing

In Evaluation & Benchmarks

Citations in the corpus

All-but-the-Top: Simple and Effective Postprocessing for Word Representations (2017, background): “…and the processed TSCCA word representations in German and Spanish on three German similarity datasets (GUR65 – a German version of the RG65 dataset, GUR350, and ZG222 in terms of relatedness) (Zesch and Gurevych, 2006) and the Spanish version of RG65 dataset (Camacho-Collados et al., 2015).”
Unsupervised Morphology Induction Using Word Embeddings (2015, methodology): “For German, we use the Gur350 and ZG222 datasets (Zesch and Gurevych, 2006).”
Wikipedia-based Semantic Interpretation for Natural Language Processing (2009, background): “Recently, Zesch and Gurevych (2006) discussed automatic creation of datasets for assessing semantic”