In this paper, we focus on the domain-specific translation with low resources, where in-domain parallel corpora are scarce or nonexistent. One common and effective strategy for this case is exploiting in-domain monolingual data with the back-translation method.
Oct 6, 2020
Abstract. In this paper, we focus on the domain-specific translation with low resources, where in-domain parallel corpora are scarce or nonexistent.
People also ask
What is the difference between forward translation and back translation?
What is back translation in machine translation?
Oct 6, 2020 · This paper proposes a novel iterative domain-repaired back-translation framework, which introduces the Domain-Repair (DR) model to refine ...
Abstract: In this paper, we focus on the domain-specific translation with low resources, where in-domain parallel corpora are scarce or nonexistent.
Abstract: In this paper, we focus on the domain-specific translation with low resources, where indomain parallel corpora are scarce or nonexistent.
In this paper, we focus on the domain-specific translation with low resources, where in-domain parallel corpora are scarce or nonexistent.
Papertalk is an open-source platform where scientists share video presentations about their newest scientific results - and watch, like + discuss them.
Back translation has been shown to out-perform forward translation in the context of domain adaptation for SMT (Lambert et al., 2011), while using back ...
Oct 6, 2020 · In this work, we incorporate a Domain-Repair. (DR) model in the iterative back-translation pro- cess to fully exploit in-domain monolingual data ...
Domain-specific Multi-modal Neural Machine Translation (DMNMT) aims to translate domain-specific sentences from a source language to a target language by ...