Building a Turkish Treebank

Oflazer, Kemal; Say, Bilge; Hakkani‐Tür, Dilek; Tür, Gökhan

doi:10.1007/978-94-010-0201-1_15

Cited by 131 publications

(83 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The problem is formulated as follows: where n i represents the number of inflectional groups associated with the ith parse and G i;j represents the jth inflectional group of parse i. The baseline trigram-based model is based on two basic assumptions: 1 ð Þ root of the current word only depends on root of two previous words, and 2 ð Þ presence of sequence of IGs in the current word depend only the last IG of two previous words. Under these assumptions, P T ð Þ is re-formulated as:…”

Section: Morphological Disambiguationmentioning

confidence: 99%

See 1 more Smart Citation

A Novel Approach to Morphological Disambiguation for Turkish

Görgün

Yıldız

2011

Computer and Information Sciences II

View full text Add to dashboard Cite

In this paper, we propose a classification based approach to the morphological disambiguation for Turkish language. Due to complex morphology in Turkish, any word can get unlimited number of affixes resulting very large tag sets. The problem is defined as choosing one of parses of a word not taking the existing root word into consideration. We trained our model with well-known classifiers using WEKA toolkit and tested on a common test set. The best performance achieved is 95.61% by J48 Tree classifier.

show abstract

Section: Morphological Disambiguationmentioning

confidence: 99%

“…However, due to the large number of tags in Turkish, data sparseness is a serious problem. To cope with the data sparseness problem, morphological parses are divided into smaller parts called inflectional groups [2]. The most recent approach to the morphological disambiguation problem is presented in [3].…”

Section: Introductionmentioning

confidence: 99%

A Novel Approach to Morphological Disambiguation for Turkish

Görgün

Yıldız

2011

Computer and Information Sciences II

View full text Add to dashboard Cite

show abstract

“…Eryiǧit ve digerleri [11] Türkçe için bagımlılık çözümlemesi yapmak için yine çe-kim gruplarını kullandı. Agaç Yapılı Türkçe Derlem de [21] çekim grupları arasındaki ilişkileri kodladı.…”

Section: Biçimbirim -Sözdizim Arabirimiunclassified

Turkish Natural Language Processing

Arisoy

Saraçlar

2018

Theory and Applications of Natural Language Processing

View full text Add to dashboard Cite

“…For multilingual experiments, we use available dependency corpora from the CoNLL-X Shared Task 2006 [35] [46]. We followed the same data preparation procedure as for WSJ, where punctuation marks are taken out and only POS tag sequences are used instead of word strings.…”

Section: Data Sets Accuracy Metrics and Settingsmentioning

confidence: 99%

A Linguistics-Driven Approach to Statistical Parsing for Low-Resourced Languages

Boonkwan

Supnithi

2015

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYDeveloping a practical and accurate statistical parser for low-resourced languages is a hard problem, because it requires large-scale treebanks, which are expensive and labor-intensive to build from scratch. Unsupervised grammar induction theoretically offers a way to overcome this hurdle by learning hidden syntactic structures from raw text automatically. The accuracy of grammar induction is still impractically low because frequent collocations of non-linguistically associable units are commonly found, resulting in dependency attachment errors. We introduce a novel approach to building a statistical parser for low-resourced languages by using language parameters as a guide for grammar induction. The intuition of this paper is: most dependency attachment errors are frequently used word orders which can be captured by a small prescribed set of linguistic constraints, while the rest of the language can be learned statistically by grammar induction. We then show that covering the most frequent grammar rules via our language parameters has a strong impact on the parsing accuracy in 12 languages.

show abstract

Building a Turkish Treebank

Cited by 131 publications

References 10 publications

A Novel Approach to Morphological Disambiguation for Turkish

A Novel Approach to Morphological Disambiguation for Turkish

Turkish Natural Language Processing

A Linguistics-Driven Approach to Statistical Parsing for Low-Resourced Languages

Contact Info

Product

Resources

About