Web-Mining Defeasible Knowledge from Concessional Statements
Mining common-sense knowledge is a vital problem of artificial intelligence that forms the basis of various tasks, from information retrieval to robotics. There have been numerous initiatives to mine common-sense facts from unstructured data, more specifi
- PDF / 185,078 Bytes
- 13 Pages / 439.37 x 666.142 pts Page_size
- 8 Downloads / 190 Views
2
University of Oxford, Oxford, UK [email protected] Technische Universit¨ at Dresden, Dresden, Germany
Abstract. Mining common-sense knowledge is a vital problem of artificial intelligence that forms the basis of various tasks, from information retrieval to robotics. There have been numerous initiatives to mine common-sense facts from unstructured data, more specifically, from Web texts. However, common-sense knowledge is typically not explicitly stated in the text, as it is considered to be obvious, self-evident, and thus shared between writer and reader. We argue that certain types of defeasible common-sense knowledge (i.e., knowledge that holds in most but not all cases), in particular, beliefs and stereotypes, tend to appear in text in a particular manner: they are not explicitly manifested, unless the speakers encounter a situation that runs in contrast to their defeasible common-sense assumptions. For example, if a speaker believes that Spain is a very warm country, she may express a surprise when it snows in Bilbao. We further argue that such conceptual contradictions correspond to the linguistic relation of concession (e.g., although Bilbao is in Spain, it is snowing there today) and we present a methodology for extracting defeasible common-sense beliefs (it is not common to snow in Spain) from Web data using concessive linguistic markers. We illustrate the methodology by mining beliefs about persons and we show that we are able to extract new information compared to existing common-sense knowledge bases.
1
Introduction
Common-sense knowledge is a set of basic propositions of a very broad semantics that describe different classes and instances, their most common properties (e.g., shape, color, material, frequency, age) and how they relate to each other. For example, the following statements belong to the realm of common-sense knowledge: snow is white, London is in England, July is the seventh month of a year, children often believe in Santa Claus. From a human-oriented point of view, “a common-sense fact is a true statement about the world that is known to most humans” [13], while from the point of view of formal systems, a common-sense fact is a formalized statement about the world that is shared between all agents and is true across all applications. Mining common-sense knowledge from a variety of resources is a vital problem of artificial intelligence, it is required for common-sense reasoning which c Springer International Publishing Switzerland 2016 O. Haemmerl´ e et al. (Eds.): ICCS 2016, LNAI 9717, pp. 191–203, 2016. DOI: 10.1007/978-3-319-40985-6 15
192
A. Petrova and S. Rudolph
forms the basis for a plethora of tasks, from more applied ones, such as question answering and item recommendation, to more general ones, such as intelligent decision making, robotics and natural language understanding [1]. For example, let us consider recommender systems. Having information about a given user, e.g., his age, profession or personal traits, the system could use common-sense knowledge about
Data Loading...
