A.1 Motivation For what purpose was the dataset created? The dataset was created to further advance machine learning techniques in the field of marine science. Who created the dataset (e.g., which team, research group) and on behalf of which entity (e.g., company, institution, organization)? The dataset was created by the Deep-REAL and CSHEL labs at the University of Delaware. The sources of the data are from USGS and NOAA. Who funded the creation of the dataset? The Department of Defense funded the project under the DEPSCoR Award. A.2 Composition What do the instances that comprise the dataset represent (e.g., documents, photos, people, countries)? An instance is a sonar image (2D grid data), containing different geographic layers, each of which is a channel of the image. How many instances are there in total (of each type, if appropriate)? Does the dataset contain all possible instances or is it a sample (not necessarily random) of instances from a larger set?

This article describes FAQ FINDER, a natural language question-answering system that uses files of frequently asked questions as its knowledge base. Unlike AI question-answering systems that focus on the generation of new answers, FAQ FINDER retrieves existing ones found in frequently asked question files. Unlike information-retrieval approaches that rely on a purely lexical metric of similarity between query and document, FAQ FINDER uses a semantic knowledge base (WORDNET) to improve its ability to match question and answer. We include results from an evaluation of the system's performance and show that a combination of semantic and statistical techniques works better than any single approach.