Challenging Language-Dependent Segmentation for Arabic: An Application to Machine Translation and Part-of-Speech Tagging

By Hassan Sajjad, Fahim Dalvi, Nadir Durrani, Ahmed Abdelali, Yonatan Belinkov, Stephan Vogel. 2017

30 citations recorded by the source corpus.

Word segmentation plays a pivotal role in improving any Arabic NLP application. Therefore, a lot of research has been spent in improving its accuracy. Off-the-shelf tools, however, are: i) complicated to use and ii) domain/dialect dependent. We explore three language-independent alternatives to morphological segmentation using: i) data-driven sub-word units, ii) characters as a unit of learning, and iii) word embeddings learned using a character CNN (Convolution Neural Network). On the tasks of Machine Translation and POS tagging, we found these methods to achieve close to, and occasionally surpass state-of-the-art performance. In our analysis, we show that a neural machine translation system is sensitive to the ratio of source and target tokens, and a ratio close to 1 or greater, gives optimal performance.

Subfields: Artificial Intelligence, 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 Artificial Intelligence

In Natural Language Processing

In Machine Translation

Citations in the corpus

What do Neural Machine Translation Models Learn about Morphology? (2017, methodology): “Here we focus on a character CNN which has been used in language modeling and machine translation (Kim et al., 2015; Belinkov and Glass, 2016; Costa-juss`a and Fonollosa, 2016; Jozefow-icz et al., 2016; Sajjad et al., 2017).”
Synthetic and Natural Noise Both Break Neural Machine Translation (2017, background): “It was shown to perform well on morphologically-rich languages (Kim et al., 2015; Belinkov & Glass, 2016; Costa-jussà & Fonollosa, 2016; Sajjad et al., 2017), thanks to its ability to learn morphologically-informative representations (Belinkov et al.”
On internal language representations in deep learning: an analysis of machine translation and speech recognition (2018, methodology): “The work here aims to provide quantitative, data-driven an'Whether unsupervised word segmentation works as well as supervised morphological segmentation in neural machine translation is an open question and may well be language-specific, as recent studies have produced conflicting results [153, 291]”