How Does Language Influence Documentation Workflow? Unsupervised Word Discovery Using Translations in Multiple Languages
This work addresses the challenge of reducing transcription costs for linguists in language documentation, but it is incremental as it only shows a slight enhancement in segmentation.
The paper tackled the problem of expensive transcription in language documentation by investigating how the choice of well-resourced languages affects unsupervised word discovery, using a bilingual Mboshi-French corpus translated into four other languages; results showed a marginal improvement in segmentation quality when combining information from different bilingual models.
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.