A study of conceptual language similarity: comparison and evaluation

TL;DR

This paper investigates a novel approach to measuring language similarity based on conceptual representations, evaluating its effectiveness for classifying language pairs, and contributing to NLP research on linguistic diversity.

Contribution

It introduces and extensively evaluates a new conceptual similarity measure for languages, complementing existing lexical and typological approaches.

Findings

Conceptual similarity can effectively distinguish related languages.

The proposed measure outperforms traditional typological features in classification tasks.

The approach aids low-resource language research and linguistic typology studies.

Abstract

An interesting line of research in natural language processing (NLP) aims to incorporate linguistic typology to bridge linguistic diversity and assist the research of low-resource languages. While most works construct linguistic similarity measures based on lexical or typological features, such as word order and verbal inflection, recent work has introduced a novel approach to defining language similarity based on how they represent basic concepts, which is complementary to existing similarity measures. In this work, we study the conceptual similarity in detail and evaluate it extensively on a binary classification task.