deletions | additions       diff --git a/untitled.tex b/untitled.tex  index 3a4bf60..4fa143e 100644  --- a/untitled.tex  +++ b/untitled.tex 
...
A story is essentially a series of events. ...  In this paper, we describe our system, Eventure, that extracts event relations from children’s stories with the use of predefined extraction templates and rules, as well as concept indicators. Multiple word and sentence analysis tools such as morphological analyzers and transducers are also utilized. Section 2 describes an event relation and  the concept representation  of a story event. an event in Eventure's ontology.  This is followed by a discussion of the templates and rules used in the extraction process in Section 3. Section 4 presents an analysis of the quality of the extracted relations. The paper ends with a discussion of issues and recommendations for future work. 2 ? Knowledge Representation  some intro text...  2.1 Event Relations 
...
Table 1. Event Relations    2.2 Eventure's Ontology    3 Design and Implementation  30 stories for children age five to eight were collected from the Internet and pre-processed to reformat dialogues into direct sentences; and to split compound, complex and compound-complex sentences to simple sentences. 3 Extraction Templates  To extract event relations, different types of concepts need to be identified. These are listed in Table 2. The first four relations, namely \textit{EffectOf}, \textit{EffectOfIsState}, \textit{EventForGoalEvent} and \textit{EventForGoalState} are similar to those used in ConceptNet to describe events. \textit{Happens(f, t)} represents that a fluent \textit{f} holds at time \textit{t}. Fluent is a concept adopted from (cite) and is considered as an event in our research. The last event relation, \textit{CauseOfIsState}, is derived from the first two event relations, and is used to represent the state that a story character is in that may lead to the execution of an event. For example, \textit{CauseOfIsState(sleep, tired)} means that if a story character is \textit{tired} (a state), he/she may \textit{go to sleep} (an event).  Table 2. Concepts in Eventure    These concepts are used to define the elements that comprise an extraction template, which are shown in Table 3. The last two elements are based from McIntyre and Lapata's (cite) content planning phase for ?story generation?, and are used in Eventure to extract event relations that span across sentences.  Table 3. Elements used in Extraction Templates    3.1 Extraction Templates  12 extraction templates for event relations were defined. These templates are shown in Table 4.  Table 4. Extraction Templates for Event Relations    3.2 Extraction Rules  Each of the extraction templates has an associated set of rules (why?).  Summarize the types of rules and provide one or two example...  3.3 Pre-Processing  The corpus is comprised of 30 stories for children age five to eight that were collected from the Internet and manually pre-processed to reformat dialogues into direct sentences; and to split compound, complex and compound-complex sentences to simple sentences. The corpus is then passed to automated pre-processing for POS tagging, tokenization and co-reference resolutions are then applied, yielding the sample output in Listing 1:  Listing 1. Sample output from pre-processing module  Sample Sentence: Piglet smiled because Tigger gave him a present  Tokenizer, POS Tagger: [Piglet] [smiled] [because] [Tigger] [gave] [him] [a] [present][.]  Gazetteer: [character] [taskindicator, causeindicator] [character] [determiner]  Morphological Analyzer: [smile] [give]  Chunker: [B-NP] [B-VP] [B-SBAR] [B-NP] [B-VP] [B-NP] [I-NP] [I-NP][O] 
...
5 Conclusion and Further Work