A Machine Learning Approach for the Identification of Bengali Noun-Noun Compound Multiword Expressions

TL;DR

This paper introduces a machine learning method using Random Forests and linguistic features to identify Bengali bigram nominal compound multiword expressions in text.

Contribution

It presents a novel two-step approach combining heuristic candidate extraction with machine learning classification for Bengali MWEs.

Findings

Effective identification of Bengali bigram nominal MWEs

Utilization of association measures and WordNet-based features

High accuracy in classification results

Abstract

This paper presents a machine learning approach for identification of Bengali multiword expressions (MWE) which are bigram nominal compounds. Our proposed approach has two steps: (1) candidate extraction using chunk information and various heuristic rules and (2) training the machine learning algorithm called Random Forest to classify the candidates into two groups: bigram nominal compound MWE or not bigram nominal compound MWE. A variety of association measures, syntactic and linguistic clues and a set of WordNet-based similarity features have been used for our MWE identification task. The approach presented in this paper can be used to identify bigram nominal compound MWE in Bengali running text.