Kurdish Interdialect Machine Translation

Abstract

This research suggests a method for machine translation among two Kurdish dialects. We chose the two widely spoken dialects, Kurmanji and Sorani, which are considered to be mutually unintelligible. Also, despite being spoken by about 30 million people in different countries, Kurdish is among less-resourced languages. The research used bi-dialectal dictionaries and showed that the lack of parallel corpora is not a major obstacle in machine translation between the two dialects. The experiments showed that the machine translated texts are comprehensible to those who do not speak the dialect. The research is the first attempt for inter-dialect machine translation in Kurdish and particularly could help in making online texts in one dialect comprehensible to those who only speak the target dialect. The results showed that the translated texts are in 71% and 79% cases rated as understandable for Kurmanji and Sorani respectively. They are rated as slightly understandable in 29% cases for Kurmanji and 21% for Sorani.

Findings of the 2019 Conference on Machine Translation (WMT19)

“…With the widespread use of MT technology, there is more and more interest in training systems to translate between languages other than English. One evidence of this is the need of directly translating between pairs of similar languages, varieties, and dialects (Zhang, 1998;Marujo et al, 2011;Hassani, 2017;Costa-jussà et al, 2018). The main challenge is to take advantage of the similarity between languages to overcome the limitation given the low amount of available parallel data to produce an accurate output.…”

A Multitask-Based Neural Machine Translation Model with Part-of-Speech Tags Integration for Arabic Dialects

“…When using in-domain test set, the performance of neural MT is better than other approaches. The experiments on the out-of-domain test set revealed that the rule-based system (Spanish-to-Catalan, in BLEU) and the phrase-based system (Catalan-to-Spanish) achieved better performance Hassani [15] proposed and implemented an Intralingual Machine Translation for translating texts in Kurmani to Sorani. The author used word-for-word translation (literal or direct translation) among the dialects.…”

A Rule-Based Kurdish Text Transliteration System

“…Although confronting the problem of normalization in Kurdish seems to be addressed already in some of the previous researches such as [7], [8] and [9] as a partial task, a solution has not been proposed for transliteration task so far. For instance, in a recent work by Hassani [10], transliteration has been mentioned implicitly as one of the tasks, but no detail has been reported concretely. e task of transliteration is one of the fundamental elements in many NLP applications such as statistical machine translation, terminology extraction, cross-lingual data linking and so forth.…”