Acquiring Knowledge From Encyclopedic Texts
نویسندگان
چکیده
A computat ional model for the acquisition of knowledge from encyclopedic texts is described. The model has been implemented in a program, called SNOWY, that reads unedited texts from The World Book Encyclopedia, and acquires new concepts and conceptual relations about topics dealing with the dietary habits of animals, their classifications and habitats. The program is also able to answer an ample set of questions about the knowledge that it has acquired. This paper describes the essential components of this model, namely semantic interpretation, inferences and representation, and ends with an evaluation of the performance of the program, a sample of the questions that it is able to answer, and its relation to other programs of similar nature.
منابع مشابه
Why to Base the Knowledge Representation Language on Natural Language?
It is argued that a knowledge representation language intended to be applied across diverse domains must be based on natural language. It is also indicated that such a representation language will facilitate the acquisition of knowledge from natural language and the interaction with other programs in need of obtaining some knowledge. The main aspects of a knowledge representation language based...
متن کاملA Step toward Semantic Indexing of an Encyclopedic Corpus
This paper investigates a method for extracting and acquiring knowledge from Linguistic resources. In particular, we propose an NLP based architecture for building a semantic network out of an XML on line encyclopedic corpus. The general application underlying this work is a question-answering system on proper nouns within an encyclopedia.
متن کاملApplying a Semantic Interpreter to a Knowledge Extraction Task
A system that extracts knowledge from encyclopedic texts is presented. The knowledge extraction component is based on a semantic interpreter of English based on an enhanced WordNet. The input to the knowledge extraction component is the output of the semantic interpreter. The extraction task was chosen in order to test the semantic interpreter. The following aspects are described: the definitio...
متن کاملUsing Statistical Parsers and Wordnet Ontology for Building Semantic Structures from Encyclopedic Texts
Algorithms are described for constructing semantic structures from encyclopedic texts and other types of texts. First, sentences are parsed using a statistical parser. Then, for every main verb on the parse tree, a minimal clause structure is built. The initial clauses are refined and null elements on the parse tree are filled, by using verb subcategorization and verb semantics. Then, the seman...
متن کاملThe SynDiKATe Text Knowledge Base Generator
SynDiKATe comprises a family of text understanding systems for automatically acquiring knowledge from real-world texts, viz. information technology test reports and medical nding reports. Their content is transformed to formal representation structures which constitute corresponding text knowledge bases. SynDiKATe's architecture integrates requirements from the analysis of single sentences, as ...
متن کامل