Combining Word-Level and Character-Level Models for Machine Translation Between Closely-Related Languages

By Preslav Nakov, Jörg Tiedemann. 2012

103 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Natural Language Processing

Citations in the corpus

Edinburgh’s Phrase-based Machine Translation Systems for WMT-14 (2014, methodology): “The transliteration module can be used to translate the 50K OOV words but previous research (Durrani et al., 2010; Nakov and Tiedemann, 2012) has shown that translit-eration is useful for more than just translating OOV words when translating closely related language pairs.”
Integrating an Unsupervised Transliteration Model into Statistical Machine Translation (2014, background): “Transliteration has also shown to be useful for translating closely related language pairs (Durrani et al., 2010; Nakov and Tiedemann, 2012), and for disambiguation (Her-mjakob et al., 2008; Azab et al., 2013).”
Improving machine translation via triangulation and transliteration (2014, unknown): “Transliteration is shown to be useful when the languages in question are closely re-lated (Durrani et al., 2010; Nakov and Tiedemann, 2012).”
Do Characters Abuse More Than Words? (2016, background): “…n-grams have been proven useful for other NLP tasks such as authorship identiﬁcation (Sapkota et al., 2015), native language identiﬁcation (Tetreault et al., 2013) and machine translation (Nakov and Tiedemann, 2012), but surprisingly have not been the focus in prior work for abusive language.”
On internal language representations in deep learning: an analysis of machine translation and speech recognition (2018, methodology): “Characters and other sub-word units have become increasingly popular in neural machine translation, although they had also been used in phrase-based MT for handling morphologically-rich [220] or closely related language pairs [97, 253].”
Orthographic Syllable as basic unit for SMT between Related Languages (2016, methodology): “For instance, lexical similarity can be modelled in the standard SMT pipeline by transliteration of words while decoding (Durrani et al., 2010) or post-processing (Nakov and Tiedemann, 2012; Kunchukuttan et al., 2014).”
Who Needs Words? Lexicon-Free Speech Recognition (2019, background): “Character-based models permeated text classification [1], language modeling [2, 3, 4], machine translation [5, 6, 7, 8, 9, 10], and automatic speech recognition (ASR) [11, 12, 13].”
Challenging Language-Dependent Segmentation for Arabic: An Application to Machine Translation and Part-of-Speech Tagging (2017, background): “Character-based models have been found to be effective in translating closely related language pairs (Durrani et al., 2010; Nakov and Tiedemann, 2012) and OOV words (Durrani et al.”