Morphological Disambiguation by Voting Constraints

TL;DR

This paper introduces a constraint-based morphological disambiguation system that uses voting among constraints to improve accuracy and independence from rule order, demonstrated on Turkish with high precision and recall.

Contribution

The paper presents a novel voting constraint approach for morphological disambiguation that reduces rule sequencing issues and achieves high accuracy on Turkish.

Findings

Achieved 95-96% recall and 94-95% precision on Turkish disambiguation.

Used about 500 constraints and simple statistics for effective disambiguation.

System implemented in Prolog, exploring finite state transducer implementation.

Abstract

We present a constraint-based morphological disambiguation system in which individual constraints vote on matching morphological parses, and disambiguation of all the tokens in a sentence is performed at the end by selecting parses that receive the highest votes. This constraint application paradigm makes the outcome of the disambiguation independent of the rule sequence, and hence relieves the rule developer from worrying about potentially conflicting rule sequencing. Our results for disambiguating Turkish indicate that using about 500 constraint rules and some additional simple statistics, we can attain a recall of 95-96% and a precision of 94-95% with about 1.01 parses per token. Our system is implemented in Prolog and we are currently investigating an efficient implementation based on finite state transducers.