Machine Reading holds significant potential for automating knowledge capture, especially given the continuing improvements in natural-language processing technologies. Macro-reading techniques (skimming many documents) now enable collecting large databases of facts, while modern micro-reading techniques (comprehension of individual paragraphs) have proven effective at factoid question answering. In this workshop, participants will discuss ways to develop new capabilities in macro- and micro-reading to take these to the next level, in particular to extract useful representations of text (be they symbolic, neural, or a hybrid) that enable, for example, automated reasoning to answer non-trivial questions.
Machine Reading is very broad, encompassing many subdiscipines of AI, and its potential to help with knowledge capture is largely undeveloped. Here is a sample of the topics relevant to the workshop:
advances and new directions in NLP
methods of active learning for guiding machine readers to useful content
methods for (dis)confirming content derived from text
extracting content from tables and diagrams
integrating extracted information into a knowledge base
hybrids methods that combine "deep NLP" and symbolic logic
ways that macro reading might inform micro reading, and vice versa
12月04日
2017
会议日期
注册截止日期
留言