How Does Language Influence Documentation Workflow? Unsupervised Word Discovery Using Translations in Multiple Languages

TL;DR

This paper explores how translations in multiple languages affect unsupervised word discovery in language documentation, showing that well-resourced languages influence quality and combining models offers limited improvements.

Contribution

It investigates the impact of well-resourced languages on unsupervised word discovery and assesses the benefit of combining bilingual models in language documentation.

Findings

Well-resourced languages impact segmentation quality.

Combining bilingual models marginally improves results.

Translation-based approaches aid language documentation.

Abstract

For language documentation initiatives, transcription is an expensive resource: one minute of audio is estimated to take one hour and a half on average of a linguist's work (Austin and Sallabank, 2013). Recently, collecting aligned translations in well-resourced languages became a popular solution for ensuring posterior interpretability of the recordings (Adda et al. 2016). In this paper we investigate language-related impact in automatic approaches for computational language documentation. We translate the bilingual Mboshi-French parallel corpus (Godard et al. 2017) into four other languages, and we perform bilingual-rooted unsupervised word discovery. Our results hint towards an impact of the well-resourced language in the quality of the output. However, by combining the information learned by different bilingual models, we are only able to marginally increase the quality of the segmentation.