Controlling Utterance Length in NMT-based Word Segmentation with Attention
arXiv:1910.08418
Abstract
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.
Accepted to IWSLT 2019 (Hong-Kong)
References in corpus (7)
- Sequence to Sequence Learning with Neural Networks
- Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
- Structured Attention Networks
- Temporal Attention Model for Neural Machine Translation
- Implicit Distortion and Fertility Models for Attention-based Encoder-Decoder NMT Model
- Learning to Segment Inputs for NMT Favors Character-Level Processing
- Neural Machine Translation with Recurrent Attention Modeling