Comparative Error Analysis in Neural and Finite-state Models for Unsupervised Character-level Transduction

TL;DR

This paper compares finite-state and sequence-to-sequence models for unsupervised character-level transduction, revealing different error patterns and exploring hybrid decoding approaches across multiple language tasks.

Contribution

It provides a detailed error analysis of both model types in unsupervised settings and examines the impact of combining them during decoding.

Findings

Finite-state and sequence-to-sequence models make different error types.

Hybrid decoding can improve transduction quality.

Models perform comparably but differ in error distribution.

Abstract

Traditionally, character-level transduction problems have been solved with finite-state models designed to encode structural and linguistic knowledge of the underlying process, whereas recent approaches rely on the power and flexibility of sequence-to-sequence models with attention. Focusing on the less explored unsupervised learning scenario, we compare the two model classes side by side and find that they tend to make different types of errors even when achieving comparable performance. We analyze the distributions of different error classes using two unsupervised tasks as testbeds: converting informally romanized text into the native script of its language (for Russian, Arabic, and Kannada) and translating between a pair of closely related languages (Serbian and Bosnian). Finally, we investigate how combining finite-state and sequence-to-sequence models at decoding time affects the output quantitatively and qualitatively.