Source and Translation Classification using Most Frequent Words

By Zahurul Islam, Armin Hoenen. 2013

9 citations recorded by the source corpus.

Subfields: Natural Language Processing, 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 Natural Language Processing

1. Marcello Federico
2. Mauro Cettolo
3. Nicola Bertoldi
4. Yonatan Belinkov
5. Rico Sennrich
6. Philipp Koehn
7. Nadir Durrani
8. Jan Niehues

In Machine Translation

1. Mauro Cettolo
2. Marcello Federico
3. Yonatan Belinkov
4. Hassan Sajjad
5. Fahim Dalvi
6. Nadir Durrani

Citations in the corpus

• MURAL: Multimodal, Multitask Retrieval Across Languages (2021, neutral): “It also suggests that it may be worth trying to improve multimodal, multilingual representations for a given lower-resource language by pivoting on a wellresourced language that is linguistically related or which has been in significant contact with it– similar to previous studies for machine transl”
• The repetition rate of text as a predictor of the effectiveness of machine translation adaptation (2014, background): “…the proportion of syllables per word, lexical richness, and information load as the proportion of lexical words to tokens in (Ilisei et al., 2010); most frequent words and a list of some hundred function words are instead used in (Islam and Hoenen, 2013) and (Koppel and Ordan, 2011), respectively.”