 |
|
User loginSearch the SiteSearch Member Database |
helenahUsername: helenahParticipant details
Research InterestsMy area of interest is Natural Language Processing (NLP). In the past I worked in the areas of Machine Translation and Dialog Systems. In the recent times I have been interested in applying Machine Learning algorithms and Statistical Analysis to NLP problems, as well as in Machine Learning and Statistics in itself. This interest is tightly connected with the tasks I had to solve for my PhD research. My thesis is in the area of Recognizing Textual Entailment(RTE). The majority of work in the area of RTE is focused on finding out a generic solution to the task. That is, creating a system that uses exactly same algorithm to return a yes or no answer for all textual entailment pairs. In my thesis I estimate the benefit of adding components to a generic RTE system that are designed specifically for the entailment pairs that are recognized poorly by the majority of the existing generic systems. I use a uniform way of work with selected groups of entailment pairs rather than a patch for a particular case. First I give definition to the group of entailment pairs, then I create a machine learner that automatically distinguishes the entailment pairs of interest from all other entailment pairs. Next an RTE engine is build for this particular group of entailment pairs and the evaluation of its work performed. The thesis contains results for two different groups of entailment pairs, a model of a generic system and evaluation of the impact of addition of those two independent components on the generic system. ____________________________Recognizing Textual Entailment (RTE) is a task where, given two text snippets, the goal is to determine whether the meaning of one text snippet can be inferred from the meaning of the other. The first of the text snippets in such a pair is referred to as the text and the other one as the hypothesis. The pair of text and hypothesis is called a text-hypothesis pair or entailment pair, with the two names considered to be synonymous. The text is usually much longer than the hypothesis. It can be represented by one or more coherent sentences, while the hypothesis is usually one short sentence. It is the meaning of the hypothesis that might or might not be entailed from the text. Thus, given a text-hypothesis pair, we recognize the relation between the meanings of the text and the hypothesis in the pair as a true entailment if the meaning of the hypothesis is entailed from the meaning of the text. Otherwise, we recognize the relation between the meanings of the texts as a false entailment. Representative Publicationshttp://www.ics.mq.edu.au/~elena/AkhmDrasALTA07.pdf http://www.ics.mq.edu.au/~elena/LNCSAkhmatovaMolla.pdf Publications page: http://www.ics.mq.edu.au/~elena/pub.html
Member for: 5 years 3 weeks 3 days |
