In this paper, we describe experiments conducted on identifying a person using a novel unique correlated corpus of text and audio samples of the person's communication in six genres. The text samples include essays, emails, blogs, and chat. Audio samples were collected from individual interviews and group discussions and then transcribed to text. For each genre, samples were collected for six topics. We show that we can identify the communicant with an accuracy of 71% for six fold cross validation using an average of 22,000 words per individual across the six genres. For person identification in a particular genre (train on five genres, test on one), an average accuracy of 82% is achieved. For identification from topics (train on five topics, test on one), an average accuracy of 94% is achieved. We also report results on identifying a person's communication in a genre using text genres only as well as audio genres only.

________________________________________________________________________Content extraction systems can automatically extract entities and relations from raw text and use the information to populate knowledge bases, potentially eliminating the need for manual data discovery and entry. Unfortunately, content extraction is not sufficiently accurate for end-users who require high trust in the information uploaded to their databases, creating a need for human validation and correction of extracted content. In this paper, we examine content extraction errors and explore their influence on a prototype semi-automated system that allows a human reviewer to correct and validate extracted information before uploading it, focusing on the identification and correction of precision errors. We applied content extraction to six different corpora and used a Goals, Operators, Methods, and Selection rules Language (GOMSL) model to simulate the activities of a human using the prototype system to review extraction results, correct precision errors, ignore spurious instances, and validate information. We compared the simulated task completion rate of the semi-automated system model with that of a second GOMSL model that simulates the steps required for finding and entering information manually. Results quantify the efficiency advantage of the semi-automated workflow and illustrate the value of employing multidisciplinary quantitative methods to calculate system-level measures of technology utility.

No abstract

No abstract

Important information from unstructured text is typically entered manually into knowledge bases, resulting in limited quantities of data. Automated information extraction from the text could assist with this process, but the technology is still at unacceptable accuracies. This task therefore requires a suitable user interface to allow for correction of the frequent extraction errors and validation of proposed assertions that a user wants to enter into a knowledge base. In this paper, we discuss our system for semi-automatic database population and how it handles the issues arising in content extraction and populating a knowledge base. The main contributions of this work are identifying the challenges in building such a semi-automated tool, the categorization of extraction errors, addressing the gaps in current extraction technology required for databasing, and the design and development of a usable interface and system, FEEDE, to support correcting content extraction output and speeding up the data entry time into knowledge bases. To our knowledge, this is the first effort to populate knowledge bases using content extraction from unstructured text.