Explanation Knowledge Graph Construction Through Causality Extraction from Texts

Explanation knowledge expressed by a graph,especially in the graphical model,is essential to comprehend clearly all paths of effect events in causality for basic diagnosis.This research focuses on determining the effect boundary using a statistical based approach and patterns of effect events in the graph whether they are consequence or concurrence without temporal markers.All necessary causality events from texts for the graph construction are extracted on multiple clauses/EDUs（Elementary Discourse Units） which assist in determining effect-event patterns from written event sequences in documents.To extract the causality events from documents,it has to face the effect-boundary determination problems after applying verb pair rules（a causative verb and an effect verb） to identify the causality.Therefore,we propose Bayesian Network and Maximum entropy to determine the boundary of the effect EDUs.We also propose learning the effect-verb order pairs from the adjacent effect EDUs to solve the effect-event patterns for representing the extracted causality by the graph construction.The accuracy result of the explanation knowledge graph construction is 90%based on expert judgments whereas the average accuracy results from the effect boundary determination by Bayesian Network and Maximum entropy are 90%and 93%,respectively.

Mining Causality for Explanation Knowledge from Text

Mining causality is essential to provide a diagnosis within multiple sentences or EDUs （Elementary Discourse Unit） This research aims at extracting the causality existing The research emphasizes the use of causality verbs because they make explicit in a certain way the consequent events of a cause, e.g., ＂Aphids suck the sap from rice leaves. Then leaves will shrink. Later, they will become yellow and dry.＂. A verb can also be the causal-verb link between cause and effect within EDU（s）, e.g., ＂Aphids suck the sap from rice leaves causing leaves to be shrunk＂ （＂causing＂ is equivalent, to a causal-verb link in Thai）. The research confronts two main problems： identifying the interesting causality events from documents and identifying their boundaries. Then, we propose mining on verbs by using two different machine learning techniques, Naive Bayes classifier and Support Vector Machine. The resulted mining rules will be used for the identification and the causality extraction of the multiple EDUs from text. Our multiple EDUs extraction shows 0.88 precision with 0.75 recall from Naive Bayes classifier and 0.89 precision with 0.76 recall from Support Vector Machine.