Disentangling Words, Clitics, and Suffixes in Uyghur

Suffixes, Conjugates and Lyndon Words

Norwegian Possessive Pronouns: Phrases, Words or Suffixes?

In Norwegian, possessive pronouns can be prenominal (min bil 'my car') or postnominal (bilen min 'car.DEF my'). In the Principles and Parameters literature, the standard assumption is that possessive pronouns are prenominal in underlying structure, while the postnominal position is a result of N-movement. This paper takes a different approach. The focus is the grammatical differences between th...

Detection of Loan Words in Uyghur Texts

For low-resource languages like Uyghur, data sparseness is always a serious problem in related information processing, especially in some tasks based on parallel texts. To enrich bilingual resources, we detect Chinese and Russian loan words from Uyghur texts according to phonetic similarities between a loan word and its corresponding donor language word. In this paper, we propose a novel approa...

A Method for Recognizing Radicals and Suffixes of Unknown Words

The authors suggest an approach to the learning of new words and new variations of known words in natural language morphological analysis. This method focuses on the determination of radicals and suffixes of words, and is implemented by splitting each word into a list of all possible radical/suffix pairs whereby the most promising of them is determined comparing certainty degrees. The calculus ...

Learning Distributed Representations of Uyghur Words and Morphemes

While distributed representations have proven to be very successful in a variety of NLP tasks, learning distributed representations for agglutinative languages such as Uyghur still faces a major challenge: most words are composed of many morphemes and occur only once on the training data. To address the data sparsity problem, we propose an approach to learn distributed representations of Uyghur...