The suitability of different parsing methods for different languages is an important topic in syntactic parsing. Especially lesser-studied languages, typologically different from the languages for which methods have originally been developed, poses interesting challenges in this respect. This article presents an investigation of data-driven dependency parsing of Turkish, an agglutinative free constituent order language that can be seen as the representative of a wider class of languages of similar type. Our investigations show that morphological structure plays an essential role in finding syntactic relations in such a language. In particular, we show that employing sublexical representations called inflectional groups, rather than word forms, as the basic parsing units improves parsing accuracy. We compare two different parsing methods, one based on a probabilistic model with beam search, the other based on discriminative classifiers and a deterministic parsing strategy, and show that the usefulness of sublexical units holds regardless of parsing method. We examine the impact of morphological and lexical information in detail and show that, properly used, this kind of information can improve parsing accuracy substantially. Applying the techniques presented in this article, we achieve the highest reported accuracy for parsing the Turkish Treebank.

This paper presents a semiautomatic technique for developing broad-coverage finite-state morphological analyzers for use in natural language processing applications. It consists of three components—elicitation of linguistic information from humans, a machine learning bootstrapping scheme, and a testing environment. The three components are applied iteratively until a threshold of output quality is attained. The initial application of this technique is for the morphology of low-density languages in the context of the Expedition project at NMSU Computing Research Laboratory. This elicit-build-test technique compiles lexical and inØectional information elicited from a human into a finite-state transducer lexicon and combines this with a sequence of morphographemic rewrite rules that is induced using transformation-based learning from the elicited examples. The resulting morphological analyzer is then tested against a test set, and any corrections are fed back into the learning procedure, which then builds an improved analyzer.

We present a human judgments dataset and an adapted metric for evaluation of Arabic machine translation. Our mediumscale dataset is the first of its kind for Arabic with high annotation quality. We use the dataset to adapt the BLEU score for Arabic. Our score (AL-BLEU) provides partial credits for stem and morphological matchings of hypothesis and reference words. We evaluate BLEU, METEOR and AL-BLEU on our human judgments corpus and show that AL-BLEU has the highest correlation with human judgments. We are releasing the dataset and software to the research community.

This paper presents an approach to spelling correction in agglutinative languages that is based on two-level morphology and a dynamic programming based search algorithm. Spelling correction in agglutinative languages is signi cantly di erent than in languages like English. The concept of a word in such languages is much wider that the entries found in a dictionary, owing to productive word formation by derivational and in ectional a xations. After an overview of certain issues and relevant mathematical preliminaries, we formally present the problem and our solution. We then present results from our experiments with spelling correction in Turkish, a Ural{Altaic agglutinative language.Our results indicate that we can nd the intended correct word in 95% of the cases and o er it as the rst candidate in 74% of the cases, when the edit distance is 1.

In this paper, we present a statistical machine translation system for English to Dialectal Arabic (DA), using Modern Standard Arabic (MSA) as a pivot. We create a core system to translate from English to MSA using a large bilingual parallel corpus. Then, we design two separate pathways for translation from MSA into DA: a two-step domain and dialect adaptation system and a one-step simultaneous domain and dialect adaptation system. Both variants of the adaptation systems are trained on a 100k sentence tri-parallel corpus of English, MSA, and Egyptian Arabic generated by a rule-based transformation. We test our systems on a held-out Egyptian Arabic test set from the 100k sentence corpus and we achieve our best performance using the two-step domain and dialect adaptation system with a BLEU score of 42.9.