This paper addresses the approach named dependency relations to identify the position of words located in compound noun as a head modifier or modifier head. To identify correctly the head modifier in the words, the type of relationships needs to be used. Currently, there are a few outstanding parsers available to analyze the input sentence in the structure of dependency triples, hierarchy of typed dependencies and syntactic level of words. All these kinds of structures are useful in our research work. However, the output generated is in an English form. Extensive research and development are needed to adopt them in our localized data. The data gathered need to be analyzed before being executed in the next process of checking the head and modifier relations between words. In this situation, not all the relations used in the three structures above are used in our research work. We have to choose only the most relevant relations, those which can assist us to solve the problems. The effectiveness of the relations used in our study can be measured using recall, precision and F1-score techniques. The comparison of the baseline values is important, so that whether or not there has been an improvement in a result can be seen.