A notably challenging problem related to event processing is recognizing the relations holding between events in a text, in particular temporal and causal relations. While there has been some research on temporal relations, the aspect of causality between events from a Natural Language Processing (NLP) perspective has hardly been touched. We propose an annotation scheme to cover different types of causality between events, techniques for extracting such relations and an investigation into the connection between temporal and causal relations. In this thesis work we aim to focus especially on the latter, because causality is presumed to have a temporal constraint. We conjecture that injecting this presumption may be beneficial for the recognition of both temporal and causal relations.
Extracting Temporal and Causal Relations between Events
Paramita, Paramita
2014-01-01
Abstract
A notably challenging problem related to event processing is recognizing the relations holding between events in a text, in particular temporal and causal relations. While there has been some research on temporal relations, the aspect of causality between events from a Natural Language Processing (NLP) perspective has hardly been touched. We propose an annotation scheme to cover different types of causality between events, techniques for extracting such relations and an investigation into the connection between temporal and causal relations. In this thesis work we aim to focus especially on the latter, because causality is presumed to have a temporal constraint. We conjecture that injecting this presumption may be beneficial for the recognition of both temporal and causal relations.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.