1 |
Controlling Utterance Length in NMT-based Word Segmentation with Attention
|
|
|
|
In: International Workshop on Spoken Language Translation ; https://hal.archives-ouvertes.fr/hal-02343206 ; International Workshop on Spoken Language Translation, Nov 2019, Hong-Kong, China (2019)
|
|
Abstract:
International audience ; One of the basic tasks of computational language documentation (CLD) is to identifyword boundaries in an unsegmented phonemic stream. While several unsupervisedmonolingual word segmentation algorithms exist in the literature,they are challenged in real-world CLD settings by the small amount of availabledata. 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 compareways 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.
|
|
Keyword:
[INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL]; [INFO]Computer Science [cs]; Computational Language Documentation; Machine Translation; Word Segmentation
|
|
URL: https://hal.archives-ouvertes.fr/hal-02343206 https://hal.archives-ouvertes.fr/hal-02343206/file/IWSLT2019_paper_5.pdf https://hal.archives-ouvertes.fr/hal-02343206/document
|
|
BASE
|
|
Hide details
|
|
2 |
Unsupervised word discovery for computational language documentation ; Découverte non-supervisée de mots pour outiller la linguistique de terrain
|
|
|
|
In: https://tel.archives-ouvertes.fr/tel-02286425 ; Artificial Intelligence [cs.AI]. Université Paris Saclay (COmUE), 2019. English. ⟨NNT : 2019SACLS062⟩ (2019)
|
|
BASE
|
|
Show details
|
|
3 |
Controlling Utterance Length in NMT-based Word Segmentation with Attention ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Controlling Utterance Length in NMT-based Word Segmentation with Attention ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Controlling Utterance Length in NMT-based Word Segmentation with Attention ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|