Exploiting Morphology and Local Word Reordering in English-to-Turkish Phrase-Based Statistical Machine Translation

Abstract

Abstract-In this paper, we present the results of our work on the development of a phrase-based statistical machine translation prototype from English to Turkish-an agglutinative language with very productive inflectional and derivational morphology. We experiment with different morpheme-level representations for English-Turkish parallel texts. Additionally, to help with word alignment, we experiment with local word reordering on the English side, to bring the word order of specific English prepositional phrases and auxiliary verb complexes, in line with the morpheme order of the corresponding case-marked nouns and complex verbs, on the Turkish side. To alleviate the dearth of the parallel data available, we also augment the training data with sentences just with content word roots obtained from the original training data to bias root word alignment, and with highly reliable phrase-pairs from an earlier corpus alignment. We use a morpheme-based language model in decoding and a word-based language model in re-ranking the -best lists generated by the decoder. Lastly, we present a scheme for repairing the decoder output by correcting words which have incorrect morphological structure or which are out-of-vocabulary with respect to the training data and language model, to further improve the translations. We improve from 15.53 BLEU points for our word-based baseline model to 25.17 BLEU points for an improvement of 9.64 points or about 62% relative.Index Terms-Complex morphology, English, statistical machine translation (SMT), Turkish, word reordering.

Turkish Natural Language Processing

“…Bunun içinŞekil 7'de görülen ve Agaç Yapılı Türkçe Derlem'deki tümceleri nasıl kodlandıgını daŞ ekil 8:Şekil 7'deki bir sözcügün birden fazla iliş-kisi gösteren örnege bakılmasını öneriririz. 9 Buşekilde düz çizgili oval dörtgenler sözcükleri ve kırık çizgili oval dörtgenler ise çekim gruplarını göstermektedir. Önce de söyledigimiz gibi ilişki oku her sözcükte son çekim grubundan çıkmakta ve (genelde sagda bulunan) başka bir sözcügün çekim gruplarından bir tanesine gitmektedir.…”

“…. yap +ama +yacak +tı +m Bu yaklaşım Durgar-El Kahlout'un doktora tezinde [8], ve öncesi ve sonrasındaki çeşitli yayınlarda [18,8,9] Moses çeviri sistemi [14] kullanılarak denendi. Her ne kadar sözcük tabanlı bir sistemle karsılaştırıldıgında oldukça iyi ilerlemeler kaydedilmiş olsa da başka bazı önemli problemler de gözlendi:…”

A Survey of Word Reordering in Statistical Machine Translation: Computational Models and Language Phenomena

“…Knowledge-Based Pre-ordering. In these approaches, manually written rules determine the transformation of input syntax trees (Collins, Koehn, and Kucerova 2005;Wang, Collins, and Koehn 2007;Xu et al 2009;Isozaki et al 2010b;Yeniterzi and Oflazer 2010;Gojun and Fraser 2012;Andreas, Habash, and Rambow 2011) or the permutation of shallow syntactic chunks in a sentence (Hardmeier, Bisazza, and Federico 2010;Durgar El-Kahlout and Oflazer 2010;Bisazza, Pighin, and Federico 2012). In an early example of syntax-based pre-ordering, Collins, Koehn, and Kucerova (2005) propose a set of six rules aimed at arranging German sentences in English-like order.…”

A tree-based approach for English-to-Turkish translation

“…In phrase-based models, the main unit to be translated is the phrase. Some works, such as [1][2][3][4][5], apply this approach to translate from English to Turkish. However, a disadvantage of this approach is that as the number of words intervening between the related words increases, the phrase-based approach fails to link those related words.…”