Requirements terminology defines and unifies key specialized and/or technical concepts of the software system, which is significant for understanding the application domian in early phase requirements engineering (RE). However, manual terminology extraction from natural language requirements is laborious and expensive, especially with large scale requirements specifications. In this paper, we aim to employ natural language processing (NLP) techniques and machine learning (ML) algorithms to automatically extract and rank the requirements terms to support high-level domain modeling. To this end, we propose an automatic framework composed of noun phrase chunking technique for requirements terms extraction and TextRank combined with semantic similarity for terms ranking. The final ranked terms have the hierarchical characteristic and can be used to model software features. In the quantitative evaluation, our extraction method significantly outperform three baseline methods in recall with comparable precision. Moreover, our adapted TextRank algorithm can rank more correct terms at the top positions according to abstract level in terms of mean average precision. A case study on the smart home domain demonstrates the usefulness of our framework in aiding feature modeling. The research results suggest that proper adoption and adaption of NLP and ML techniques according to the characteristic of specific RE task could provide automation support for problem domain understanding in early phase RE.