An evaluation of help mechanisms in natural language information retrieval systems

The field of natural language processing (NLP) demonstrates rapid changes in the design of information retrieval systems and human‐computer interaction. While natural language is being looked on as the most effective tool for information retrieval in a contemporary information environment, the systems using it are only beginning to emerge. This study attempts to evaluate the current state of NLP IR systems from the user’s point of view: what techniques are used by these systems to guide their users through the search process? The analysis focused on the structure and components of the systems’ help mechanisms. Results of the study demonstrated that systems which claimed to be using natural language searching in fact used a wide range of information retrieval techniques from real natural language processing to Boolean searching. As a result, the user assistance mechanisms of these systems also varied. While pseudo‐NLP systems would suit a more traditional method of instruction, real NLP systems primarily utilised the methods of explanation and user‐system “dialogue”.