Conference paper Open Access

Controlling Utterance Length in NMT-based Word Segmentation with Attention

Godard, Pierre; Besacier, Laurent; Yvon, François

Dublin Core Export

<?xml version='1.0' encoding='utf-8'?>
<oai_dc:dc xmlns:dc="" xmlns:oai_dc="" xmlns:xsi="" xsi:schemaLocation="">
  <dc:creator>Godard, Pierre</dc:creator>
  <dc:creator>Besacier, Laurent</dc:creator>
  <dc:creator>Yvon, François</dc:creator>
  <dc:description>One of the basic tasks of computational language documentation (CLD) is to identify word boundaries in an unsegmented phonemic stream. While several unsupervised monolingual word segmentation algorithms exist in the literature, they are challenged in real-world CLD settings by the small amount of available data. A possible remedy is to take advantage of glosses or translation in a foreign, well- resourced, language, which often exist for such data. In this paper, we explore and compare ways to exploit neural machine translation models to perform unsupervised boundary detection with bilingual information, notably introducing a new loss function for jointly learning alignment and segmentation. We experiment with an actual under-resourced language, Mboshi, and show that these techniques can effectively control the output segmentation length.</dc:description>
  <dc:title>Controlling Utterance Length in NMT-based Word Segmentation with Attention</dc:title>
All versions This version
Views 7267
Downloads 4242
Data volume 23.4 MB23.4 MB
Unique views 6762
Unique downloads 4040


Cite as