Multi-Source Neural Machine Translation with Missing Data
By Yuta Nishimura, Katsuhito Sudoh, Graham Neubig, Satoshi Nakamura. 2018
56 citations recorded by the source corpus.
Multi-source translation is an approach to exploit multiple inputs (e.g. in two different languages) to increase translation accuracy. In this paper, we examine approaches for multi-source neural machine translation (NMT) using an incomplete multilingual corpus in which some translations are missing. In practice, many multilingual corpora are not complete due to the difficulty to provide translations in all of the relevant languages (for example, in TED talks, most English talks only have subtitles for a small portion of the languages that TED supports). Existing studies on multi-source translation did not explicitly handle such situations. This study focuses on the use of incomplete multilingual corpora in multi-encoder NMT and mixture of NMT experts and examines a very simple implementation where missing source translations are replaced by a special symbol . These methods allow us to use incomplete corpora both at training time and test time. In experiments with real incomplete multilingual corpora of TED Talks, the multi-source NMT with the tokens achieved higher translation accuracies measured by BLEU than those by any one-to-one NMT systems.
Subfields: Artificial Intelligence, Machine Translation
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Chris Brockett
- Michel Galley
- Yizhe Zhang
- Chenhui Chu
- Jianfeng Gao
- Anoop Kunchukuttan
- Raj Dabre
- Bill Dolan
In Machine Translation
Citations in the corpus
- Complete Multilingual Neural Machine Translation (2020, neutral): “Although multi-source NMT is a promising direction, it has practical problems such as lacking multiple sources at inference time (Nishimura et al., 2018).”
- Automatic Document Sketching: Generating Drafts from Analogous Texts (2021, background): “…to generate an abstractive text summary of multiple input documents (Liu and Lapata, 2019; Chu and Liu, 2019), and multi-source machine translation (Nishimura et al., 2018; Garmash and Monz, 2016) that encodes input texts in multiple source languages and translates them into a target language.”
- Neural Machine Translation for Low-resource Languages: A Survey (2021, background): “This restriction can be relaxed by either marking a corresponding sentence as null if a particular language does not have that sentence [142] or by generating the missing sentences with a pre-trained model [141].”
- A Survey of Multilingual Neural Machine Translation (2019, methodology): “Typical approaches are: re-ranking outputs from independent source-target systems (Och and Ney, 2001), composing a new output from independent source-target outputs (Matusov et al., 2006), and translating a combined input representation of multiple sources using lattice networks over multiple…”