Distributional Similarity of Words with Different Frequencies

Distributional semantics tries to characterize the meaning of words by the contexts in which they occur. Similarity of words hence can be derived from the similarity of contexts. Contexts of a word are usually vectors of words appearing near to that word in a corpus. It was observed in previous research that similarity measures for the context vectors of two words depend on the frequency of these words. In the present paper we investigate this dependency in more detail for one similarity measure, the Jensen-Shannon divergence. We give an empirical model of this dependency and propose the deviation of the observed Jensen-Shannon divergence from the divergence expected on the basis of the frequencies of the words as an alternative similarity measure. We show that this new similarity measure is superior to both the Jensen-Shannon divergence and the cosine similarity in a task, in which pairs of words, taken from Wordnet, have to be classified as being synonyms or not.

Linguistische und psychodidaktische Grundlagen des Fremdsprachenlernens im Seniorenalter

The article is an introduction to the discussion about the linguistic and psychodidactic concepts justifying the thesis that the senior language learners are able to learn foreign languages and that they can achieve educational success in the process of foreign language learning.

Linguistische Analekten

Salomo Löwisohn

Linguistische Beobachtungen vom unteren und mittleren Kongo

von Carl Mense

Kulturpflanzen und Hausthiere in ihrem Uebergang aus Asien nach Griechenland und Italien sowie in das übrige Europa. Historisch-linguistische Skizzen

Mode of access: Internet.

Über der Ursprung der Sprache; eine physiologisch-linguistische Studie.

Cover-title.

Linguistische Einleitung in das Studium der Bücher des A. T. mit einer Anwendung auf die jüdisch-palästinisch Schreibart der N. Testamentlichen Schriftsteller /

Mode of access: Internet.