Information Extraction, Summarization and Question Answering

SAFT: Deep Reading Throughout the Semantic Analysis and Filtering of Text

 Historical Research

Most language technology deals with large volumes of text, and overcomes gaps, omissions and idiosyncratic phrasing in any threat by finding semantically equivalent material in other texts. But when the challenge is to interpret a single text or a small set, deeper reading of each sentence is required. This project investigates various aspects of such deeper reading, including semantic frame-based interpretation; the detection of full and partial event and entity coreference; relation harvesting to fill frames; information extraction and inference; gap-filling, expectation postulation, and various aspects of support from large background knowledge; and novelty and anomaly detection.