Publishing Partner: Cambridge University Press CUP Extra Publisher Login
amazon logo
More Info

New from Oxford University Press!


May I Quote You on That?

By Stephen Spector

A guide to English grammar and usage for the twenty-first century, pairing grammar rules with interesting and humorous quotations from American popular culture.

New from Cambridge University Press!


The Cambridge Handbook of Endangered Languages

Edited By Peter K. Austin and Julia Sallabank

This book "examines the reasons behind the dramatic loss of linguistic diversity, why it matters, and what can be done to document and support endangered languages."

Academic Paper

Title: Directional distributional similarity for lexical inference
Author: Lili Kolterman
Institution: Bar-Ilan University
Author: Ido Dagan
Institution: Bar-Ilan University
Author: Idan Szpektor
Institution: Yahoo! Research
Author: Maayan Zhitomirsky-Geffet
Institution: Bar-Ilan University
Linguistic Field: Semantics; Text/Corpus Linguistics
Abstract: Distributional word similarity is most commonly perceived as a symmetric relation. Yet, directional relations are abundant in lexical semantics and in many Natural Language Processing (NLP) settings that require lexical inference, making symmetric similarity measures less suitable for their identification. This paper investigates the nature of directional (asymmetric) similarity measures that aim to quantify distributional feature inclusion. We identify desired properties of such measures for lexical inference, specify a particular measure based on Average Precision that addresses these properties, and demonstrate the empirical benefit of directional measures for two different NLP datasets.


This article appears IN Natural Language Engineering Vol. 16, Issue 4, which you can READ on Cambridge's site .

Add a new paper
Return to Academic Papers main page
Return to Directory of Linguists main page