The NETSPEAK WORDGRAPH: Visualizing keywords in context

Abstract

NETSPEAK helps writers in choosing words while writing a text. It checks for the commonness of phrases and allows for the retrieval of alternatives by means of wildcard queries. To support such queries, we implement a scalable retrieval engine, which returns high-quality results within milliseconds using a probabilistic retrieval strategy. The results are displayed as WORDGRAPH visualization or as a textual list. The graphical interface provides an effective means for interactive exploration of search results using filter techniques, query expansion and navigation. Our observations indicate that, of three investigated retrieval tasks, the textual interface is sufficient for the phrase verification task, wherein both views support context-sensitive word choice, and the WORDGRAPH best supports the exploration of a phrase's context or the underlying corpus. The preferred view for context-sensitive word choice seems to depend on query complexity (i.e. the number of wildcards in a query).