This paper presents a supervised machine learning approach to morphological analysis of Amharic verbs. We use Inductive Logic Programming (ILP), implemented in CLOG. CLOG learns rules as a first order predicate decision list. Amharic, an under-resourced African language, has very complex inflectional and derivational verb morphology, with four and five possible prefixes and suffixes respectivel...

The objective of this paper is to develop an external memory approach to extract the maximal repeats from whole genome sequences with the statistics of these repeats across classes, where the definition of a class is determined on what kind of statistics one wants to compute. We proposed a heuristic method consisted of a bucketsort-like approach and the Chinese term extraction approach. The for...

Natural language processing tasks includes summarization, machine translation, question understanding, part of speech tagging, etc. In order to achieve those tasks, a proper language representation must be defined. Roots and stems are considered as representations for some of those systems. A word needs to be processed to extract its root or stem. This paper presents a new technique that extrac...

This paper describes the results of some experiments exploring statistical methods to infer syntactic categories from a raw corpus in an unsupervised fashion. It shares certain points in common with Brown et at (1992) and work that has grown out of that: it employs statistical techniques to derive categories based on what words occur adjacent to a given word. However, we use an eigenvector deco...

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 ...

Serbian and Russian children produce fewer adjective-noun gender-agreement errors with diminutive nouns (e.g. ribica ‘little fish’) than with their simplex counterparts (e.g. riba ‘fish’). This study explores factors responsible for the diminutive advantage, using a gender-agreement task with Serbian-speaking children (N=24, mean age 4;4). Over four sessions, children were introduced to picture...