Orthographic Syllable as basic unit for SMT between Related Languages
By Anoop Kunchukuttan, Pushpak Bhattacharyya. 2016
35 citations recorded by the source corpus.
We explore the use of the orthographic syllable, a variable-length consonant-vowel sequence, as a basic unit of translation between related languages which use abugida or alphabetic scripts. We show that orthographic syllable level translation significantly outperforms models trained over other basic units (word, morpheme and character) when training over small parallel corpora.
Subfields: Machine Translation, Computational Linguistics & Semantics
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Machine Translation
- Ivan Provilkov
- Dmitrii Emelianenko
- Elena Voita
- Raj Dabre
- Chenhui Chu
- Anoop Kunchukuttan
- Marta Ruiz Costa-jussà
- Carlos Escolano
In Computational Linguistics & Semantics
- Raj Dabre
- Ivan Provilkov
- Dmitrii Emelianenko
- Chenhui Chu
- Elena Voita
- Anoop Kunchukuttan
- Pushpak Bhattacharyya
- Tamali Banerjee
Citations in the corpus
- BPE-Dropout: Simple and Effective Subword Regularization (2019, methodology): “Other segmentation algorithms include Creutz and Lagus (2006), Schuster and Nakajima (2012), Chitnis and DeNero (2015), Kunchukuttan and Bhattacharyya (2016), Wu and Zhao (2018), Banerjee and Bhattacharyya (2018).”
- A Survey of Multilingual Neural Machine Translation (2019, methodology): “Lexical similarity was utilized using subword-level translation models [85, 86, 144, 150].”
- The TALP-UPC Machine Translation Systems for WMT19 News Translation Task: Pivoting Techniques for Low Resource MT (2019, background): “Although not frequent, there are some precedents for subword tok-enization in SMT, like the work by Kunchukuttan and Bhattacharyya (2016, 2017).”
- Enabling Multi-Source Neural Machine Translation By Concatenating Source Sentences In Multiple Languages (2017, background): “The objective behind this is to determine whether or not lexical similarity, which is also one of the indicators of linguistic similarity and hence translation quality Kunchukuttan and Bhattacharyya (2016), is also an indicator of how well two source languages work together.”
- Meaningless yet meaningful: Morphology grounded subword-level NMT (2018, background): “, 2016), orthographic syllable (Kunchukuttan and Bhattacharyya, 2016), character (Chung et al.”