From Pivots to Graphs: Augmented CycleDensity as a Generalization to One Time InverseConsultation

TL;DR

This paper introduces Augmented Cycle Density (ACD), a novel framework that enhances translation prediction coverage by combining two existing methods, achieving significant improvements in multilingual translation tasks with minimal resources.

Contribution

ACD is a new framework that generalizes and combines Cycle Density and One Time Inverse Consultation for improved translation predictions without sense information or parallel corpora.

Findings

ACD achieves 74% coverage, more than double OTIC's, with similar precision.

ACD leverages multilingual graphs for scalability and minimal resource use.

Results demonstrate improved translation prediction coverage across unseen language pairs.

Abstract

This paper describes an approach used to generate new translations using raw bilingual dictionaries as part of the 4th Task Inference Across Dictionaries (TIAD 2021) shared task. We propose Augmented Cycle Density (ACD) as a framework that combines insights from two state of the art methods that require no sense information and parallel corpora: Cycle Density (CD) and One Time Inverse Consultation (OTIC). The task results show that across 3 unseen language pairs, ACD's predictions, has more than double (74%) the coverage of OTIC at almost the same precision (76%). ACD combines CD's scalability - leveraging rich multilingual graphs for better predictions, and OTIC's data efficiency - producing good results with the minimum possible resource of one pivot language.