Separated by an Un-common Language: Towards Judgment Language Informed Vector Space Modeling
This work addresses the problem of language bias in semantic evaluation for NLP researchers, highlighting a critical but often overlooked factor in model assessment.
The study translated English lexical evaluation datasets into Italian, German, and Russian and found that human judgments of word relations are strongly influenced by the language used, with monolingual vector space models not always best correlating with judgments in their training language, and multilingual models improving correlations in many cases.
A common evaluation practice in the vector space models (VSMs) literature is to measure the models' ability to predict human judgments about lexical semantic relations between word pairs. Most existing evaluation sets, however, consist of scores collected for English word pairs only, ignoring the potential impact of the judgment language in which word pairs are presented on the human scores. In this paper we translate two prominent evaluation sets, wordsim353 (association) and SimLex999 (similarity), from English to Italian, German and Russian and collect scores for each dataset from crowdworkers fluent in its language. Our analysis reveals that human judgments are strongly impacted by the judgment language. Moreover, we show that the predictions of monolingual VSMs do not necessarily best correlate with human judgments made with the language used for model training, suggesting that models and humans are affected differently by the language they use when making semantic judgments. Finally, we show that in a large number of setups, multilingual VSM combination results in improved correlations with human judgments, suggesting that multilingualism may partially compensate for the judgment language effect on human judgments.