Machine Translation (MT) is the task of mapping a source language to a target language. The recent introduction of neural MT (NMT) has shown promising results for high-resource language, however, poorly performing for low-resource language (LRL) settings. Furthermore, the vast majority of the 7, 000+ languages around the world do not
have parallel data, creating a zero-resource language (ZRL) scenario. In this thesis, we
present our approach to improving NMT for LRL and ZRL, leveraging a multilingual NMT
modeling (M-NMT), an approach that allows building a single NMT to translate across
multiple source and target languages. This thesis begins by i) analyzing the effectiveness
of M-NMT for LRL and ZRL translation tasks, spanning two NMT modeling architectures (Recurrent and Transformer), ii) presents a self-learning approach for improving the zero-shot translation directions of ZRLs, iii) proposes a dynamic transfer-learning approach from a pre-trained (parent) model to a LRL (child) model by tailoring to the
vocabulary entries of the latter, iv) extends M-NMT to translate from a source language
to specific language varieties (e.g. dialects), and finally, v) proposes an approach that
can control the verbosity of an NMT model output. Our experimental findings show the
effectiveness of the proposed approaches in improving NMT of LRLs and ZRLs.
| Identifer | oai:union.ndltd.org:unitn.it/oai:iris.unitn.it:11572/257906 |
| Date | 20 April 2020 |
| Creators | Lakew, Surafel Melaku |
| Contributors | Lakew, Surafel Melaku |
| Publisher | Università degli studi di Trento, place:Trento |
| Source Sets | Università di Trento |
| Language | English |
| Detected Language | English |
| Type | info:eu-repo/semantics/doctoralThesis |
| Rights | info:eu-repo/semantics/closedAccess |
| Relation | firstpage:1, lastpage:178, numberofpages:178 |
Page generated in 0.0024 seconds