A method for extracting causal knowledge from textual databases

This paper describes the first phase of a project to develop a knowledge extraction and knowledge discovery system that extracts causal knowledge from a textual database automatically, and attempts to infer new causal relationships from the extracted information. The initial work is focused on d...

Full description

Saved in:
Bibliographic Details
Main Authors: Chan, Syin, Niu, Yun, Ang, Alyssa, Khoo, Christopher S. G.
Other Authors: Wee Kim Wee School of Communication and Information
Format: Article
Language:English
Published: 2014
Subjects:
Online Access:https://hdl.handle.net/10356/101369
http://hdl.handle.net/10220/18370
http://www.connexor.com/nlplib/?q=node/540
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
Description
Summary:This paper describes the first phase of a project to develop a knowledge extraction and knowledge discovery system that extracts causal knowledge from a textual database automatically, and attempts to infer new causal relationships from the extracted information. The initial work is focused on developing an automatic method for identifying and extracting cause-effect information expressed in medical abstracts. Linguistic clues that indicate the presence of a causal relation in text are being identified, and linguistic patterns constructed to represent the different ways in which cause and effect are expressed in English sentences. The linguistic patterns have “slots” that indicate the parts of the sentence representing the cause and the effect. The information extraction process involves matching the linguistic patterns with the syntactic structure of sentences, and extracting the parts of the sentence that match with the slots in the patterns. The extracted information is stored in a structured manner in a “cause-effect template” that indicates the different roles and attributes of the causal situation described in the text.