Can We Derive General World Knowledge from Texts?
نویسنده
چکیده
As one attack on the “knowledge acquisition bottleneck”, we are attempting to exploit a largely untapped source of general knowledge in texts, lying at a level beneath the explicit assertional content. This knowledge consists of relationships implied to be possible in the world, or, under certain conditions, implied to be normal or commonplace in the world. The goal of the work reported is to derive such general world knowledge (initially, from Penn Treebank corpora) in two stages: first, we derive general “possibilistic” propositions from noun phrases and clauses; then we try to derive stronger generalizations, based on the nature and statistical distribution of the possibilistic claims obtained in the first phase. Here we report preliminary results of the first phase, which indicate the feasibility of our project, and its likely limitations.
منابع مشابه
What Have We Been Missing ? The Role of General World Knowledge in Discourse Processing
In recent years, memory-based and explanation-based theories have dominated the discourse processing literature. Numerous studies have been conducted to show sup port for each of the two views. Most of these studies have manipulated factors in the episodic memory trace of texts, without a great deal of focus on how general world knowledge impacts processing. We describe several studies from th...
متن کاملمدیریت دانش و ارائۀ مدلی نو
Purpose: the aim of this article is to revise the definition of the knowledge management and propose a new model. Methodology: this study depends on library texts and reviewing the existing models. Findings: the author argues that the knowledge is taken from the reality outside and it is the world of reality that is the first founder of our perception and knowledge. We capture the knowledge ...
متن کاملAn investigation into language complexity of World-of-Warcraft game-external texts
We present a language complexity analysis of World of Warcraft (WoW) community texts, which we compare to texts from a general corpus of web English. Results from several complexity types are presented, including lexical diversity, density, readability and syntactic complexity. The language of WoW texts is found to be comparable to the general corpus on some complexity measures, yet more specia...
متن کاملIntertextual Reading of Postmodern Architecture (Based on Historicist postmodern architecture and Deconstruction)
Postmodernism is a very ambiguous term. It attracted many researchers from different fields of knowledge in the late 1960s. This article explains intertextuality as a critical means to derive its concepts and components in order to understand the hidden layers of meaning in postmodern pluralist ideology. Variable thoughts of postmodern architecture have been divided into two categories—Hi...
متن کاملAbductive reasoning with temporal information
Texts in natural language contain a lot of temporal information, both explicit and implicit. Verbs and temporal adjuncts carry most of the explicit information, but for a full understanding general world knowledge and default assumptions have to be taken into account. We will present a theory for describing the relation between, on the one hand, verbs, their tenses and adjuncts and, on the othe...
متن کامل