Igor Trajkovski, PhD
Igor Trajkovski

Research


News aggregators

News aggregator is a computer-generated news site that aggregates headlines from several news sources, groups similar stories together and displays them according to each reader's personalized interests.

Traditionally, news readers first pick a publication and then look for headlines that interest them. News aggregators do things a little differently, with the goal of offering readers more personalized options and a wider variety of perspectives from which to choose.

News articles are selected and ranked by algorithms that evaluate, among other things, how often and on what sites a story appears online. Also it ranks the news articles according to certain characteristics of news content such as freshness, relevance and diversity. As a result, stories are sorted without regard to political viewpoint or ideology and you can choose from a wide variety of perspectives on any given story.

Example of a news aggregator is news.google.com. Our work is implemented in the macedonian news aggregator TIME.mk.

Query expansion for search engines

Query expansion is the process of reformulating a seed query to improve retrieval performance in information retrieval operations. In the context of web search engines, query expansion involves analysing a user's input (what words were typed into the search query area, and sometimes other types of data) and expanding the search query to match additional documents. Query expansion involves techniques such as:
  1. Finding synonyms of words, and searching for the synonyms as well
  2. Finding all the various morphological forms of words by stemming each word in the search query
  3. Fixing spelling errors and automatically searching for the corrected form or suggesting it in the results
  4. Re-weighting the terms in the original query
Our work is implemented in the macedonian search engine (frontend of Google) BORG.mk.

Machine translation

We want to automatically analyze existing human sentence translations, with an eye toward building general translation rules. We want to use these rules to translate new texts automatically.

Machine Translation (MT) is a sub-field of computational linguistics that investigates the use of computer software to translate text or speech from one natural language to another. At its basic level, MT performs simple substitution of words in one natural language for words in another. Using corpus techniques, more complex translations may be attempted, allowing for better handling of differences in linguistic typology and phrase recognition.

More precisely we are working on design and implementation of systems that translate macedonian texts into english and albanian, and vice versa.

Functional interpretation of gene expression data

Microarrays are at the center of a revolution in biotechnology, allowing researchers to simultaneously monitor the expression of tens of thousands of genes. The final aim of a typical microarray experiment is to find a molecular explanation for a given macroscopic observation (e.g., which pathways are affected by the loss of glucose in a cell, what biological processes differentiate a healthy control from a diseased case), and that is called functional interpretation of gene expression data.

The description of the enriched genesets is performed using the Gene Ontology (GO), Kyoto Encyclopedia of Genes and Genomes (KEGG) Orthology, gene annotations and gene-gene interaction data. The product of this research is SEGS (Search for Enriched Gene Sets), a web tool for descriptive analysis of microarray data.
Last Updated: 05 April 2010