This is a pre-copy-editing, author-produced PDF of an article accepted for publication in the Journal of Logic and Computation following peer review. The definitive publisher-authenticated version (Mueller, Erik T. (2004). Event calculus reasoning through satisfiability. Journal of Logic and Computation, 14(5), 703–730.) is available online at:

reasoning, reasoning about action and change This paper investigates the use of commonsense reasoning to understand texts involving stereotypical activities or scripts. We present a system that understands news stories involving four terrorism scripts. The system (1) builds a commonsense reasoning problem given an information extraction template representing a terrorist incident, and (2) uses commonsense reasoning and a commonsense knowledge base to build a model of the terrorist incident. The reasoning problem, commonsense knowledge base, and model are expressed in the classical logic event calculus. The system was developed using the MUC3 and MUC4 development data set. We present the results of running the system on the MUC3 and MUC4 test data sets, using manually generated answer key templates and templates generated automatically by two MUC4 information extraction systems. We present a detailed analysis of the models produced by the system given automatically generated templates. We present methods for answering questions based on the models produced by our system. We assess the portability of the system by extending it to handle 10 scripts frequent in Project Gutenberg American literature texts. 1

A method for automatic plot analysis of narrative texts that uses components of both traditional symbolic analysis of natural language and statistical machine-learning is presented for the story rewriting task. In the story rewriting task, an exemplar story is read to the pupils and the pupils rewrite the story in their own words. This allows them to practice language skills such as spelling, diction, and grammar without being stymied by content creation. Often the pupil improperly recalls the story. Our method of automatic plot analysis enables the tutoring system to automatically analyze the student’s story for both general coherence and specific missing events. 1

This thesis presents a method of automatic plot analysis of narrative texts that uses both components of traditional symbolic analysis of natural language and statistical machine-learning. In particular, we are investigating the story rewriting task. In the story rewriting task, an exemplar story is read to the pupils and the pupils rewrite the story in StoryStation, which allows them to concentrate more on diction and grammar than on content creation. However, often in the process of content creation the pupil improperly recalls the story. Our method of automatic plot analysis should allow the tutoring system to automatically analyze the plot of the story and provide relevant feedback to both the pupil and teacher. In the first phase

In this paper we present how the automatic extraction of events from text can be used to both classify narrative texts according to plot quality and produce advice in an interactive learning environment intended to help students with story writing. We focus on the story rewriting task, in which an exemplar story is read to the students and the students rewrite the story in their own words. The system automatically extracts events from the raw text, formalized as a sequence of temporally ordered predicate-arguments. These events are given to a machine-learner that produces a coarse-grained rating of the story. The results of the machine-learner and the extracted events are then used to generate fine-grained advice for the students. 1

Abstract not found

We describe an approach for learning a rich plan representation from a parallel corpus of commonsense narratives. Each narrative is an ordered natural language description of the steps required to accomplish common domestic tasks, including “get the mail ” and “make a bed”, and there are tens to hundreds of differently written narratives for each task. With the goal of learning a single rich plan structure, we 1) convert each narrative from English statements into a sequence of logical predicates, 2) find a global alignment for the sequences, and 3) use the sequences to construct a single underlying plan representation that can be used in language understanding problems. Doing this requires being able to distinguish different ways to accomplish the same goal from missing information, and recognize and compactly represent recurring plan sub-sequences. We describe a simple algorithm that recursively finds graph cycles by applying rules to merge nodes to learn a sequential, parameterized composition (part-of) and abstraction (is-a) plan hierarchy. We hope that these plan representations will help us learn procedural knowledge from increasingly more sophisticated text, where the sub-goals for various actions are not stated. Author Keywords Common sense, knowledge acquisition, machine reading, natural language understanding, story knowledge, plan construction, textual entailment ACM Classification Keywords H.5.2 Information Interfaces and Presentation: User Interfaces—Natural Language

This thesis describes new approaches to the formal modeling of narrative discourse. Although narratives of all kinds are ubiquitous in daily life, contemporary text processing techniques typically do not leverage the aspects that separate narrative from expository discourse. We describe two approaches to the problem. The first approach considers the conversational networks to be found in literary fiction as a key aspect of discourse coherence; by isolating and analyzing these networks, we are able to comment on longstanding literary theories. The second approach proposes a new set of discourse relations that are specific to narrative. By focusing on certain key aspects, such as agentive characters, goals, plans, beliefs, and time, these relations represent a theory-of-mind interpretation of a text. We show that these discourse relations are expressive, formal, robust, and through the use of a software system, amenable to corpus collection projects through the use of trained annotators. We have procured and released a collection of over 100 encodings, covering a set of fables as well as longer texts including literary fiction and epic poetry. We are able to inferentially find similarities and analogies between encoded stories based on the proposed relations, and an evaluation of this technique shows that human raters prefer such