Disambiguate Yourself: Supporting Users In Searching Documents With Query Disambiguation Suggestions
Ernesto William De Luca, Christian Scheel · Zenodo (CERN European Organization for Nuclear Research) · 2018
In this paper we present a query-oriented semantic approach and the respective architecture for supporting users in searching and browsing documents in a retrieval framework. While users are typing their queries a ``meaning-oriented'' analysis of each keystroke can provide different disambiguation suggestions (spelling correction, Named-Entity Recognition, WordNet- and Wikipedia-based suggestions) that can help users in formulating their queries for filtering relevant results. On the other hand systems can better interpret the query, because users implicitly tag the queries with the related meaning choosing the desired concept they had in mind. After the presentation of our architecture we show the results of two user studies, where users were asked to judge the support while typing their query and browsing documents. These results confirm that a semantic support is important in both cases.