Andrew S. Gordon

Say Anything: A Massively Collaborative Open Domain Story Writing Companion

Interactive storytelling is an interesting cross-disciplinary area that has importance in research as well as entertainment. In this paper we explore a new area of interactive storytelling that blurs the line between traditional interactive fiction and collaborative writing. We present a system where the user and computer take turns in writing sentences of a fictional narrative. Sentences contributed by the computer are selected from a collection of millions of stories extracted from Internet weblogs. By leveraging the large amounts of personal narrative content available on the web, we show that even with a simple approach our system can produce compelling stories with our users.

Using annotated video as an information retrieval interface

The ability to deliver appropriate information to learners at the most appropriate time is an essential component of good instruction. In the best learning environments, this information is received in the context of the performance of the skills that are being acquired. This paper explores a technological approach to situated information retrieval by linking materials to segments of a video recording a skill performance. An interface is described where users navigate through a video performance and are presented with information relevant to the current video location. An approach to algorithmically generating interfaces of this type is then presented. The system takes as input annotations that describe a video recording of a performance, translates these annotations into subject terms used to catalog information resources, and then retrieves materials from online database servers using the Z39.50 information retrieval protocol. As an example application, the system was used to generate online teacher professional development materials by linking annotated video of classroom teaching with resources cataloged in the ERIC database.

Say Anything: Using Textual Case-Based Reasoning to Enable Open-Domain Interactive Storytelling

We describe Say Anything, a new interactive storytelling system that collaboratively writes textual narratives with human users. Unlike previous attempts, this interactive storytelling system places no restrictions on the content or direction of the user’s contribution to the emerging storyline. In response to these contributions, the computer continues the storyline with narration that is both coherent and entertaining. This capacity for open-domain interactive storytelling is enabled by an extremely large repository of nonfiction personal stories, which is used as a knowledge base in a case-based reasoning architecture. In this article, we describe the three main components of our case-based reasoning approach: a million-item corpus of personal stories mined from internet weblogs, a case retrieval strategy that is optimized for narrative coherence, and an adaptation strategy that ensures that repurposed sentences from the case base are appropriate for the user’s emerging fiction. We describe a series of evaluations of the system’s ability to produce coherent and entertaining stories, and we compare these narratives with single-author stories posted to internet weblogs.

Recognizing Expressions of Commonsense Psychology in English Text

Many applications of natural language processing technologies involve analyzing texts that concern the psychological states and processes of people, including their beliefs, goals, predictions, explanations, and plans. In this paper, we describe our efforts to create a robust, large-scale lexical-semantic resource for the recognition and classification of expressions of commonsense psychology in English Text. We achieve high levels of precision and recall by hand-authoring sets of local grammars for commonsense psychology concepts, and show that this approach can achieve classification performance greater than that obtained by using machine learning techniques. We demonstrate the utility of this resource for large-scale corpus analysis by identifying references to adversarial and competitive goals in political speeches throughout U.S. history.

Clustering Words by Syntactic Similarity improves Dependency Parsing of Predicate-argument Structures

We present an approach for deriving syntactic word clusters from parsed text, grouping words according to their unlexicalized syntactic contexts. We then explore the use of these syntactic clusters in leveraging a large corpus of trees generated by a high-accuracy parser to improve the accuracy of another parser based on a different formalism for representing a different level of sentence structure. In our experiments, we use phrase-structure trees to produce syntactic word clusters that are used by a predicate-argument dependency parser, significantly improving its accuracy.

Automated story capture from internet weblogs

Among the most interesting ways that people share knowledge is through the telling of stories, i.e. first-person narratives about real-life experiences. Millions of these stories appear in Internet weblogs, offering a potentially valuable resource for future knowledge management and training applications. In this paper we describe efforts to automatically capture stories from Internet weblogs by extracting them using statistical text classification techniques. We evaluate the precision and recall performance of competing approaches. We describe the large-scale application of story extraction technology to Internet weblogs, producing a corpus of stories with over a billion words.

The effects of social stimuli on psychophysiological reactivity to an aversive film

Stress was induced by an aversive film, and stress responses were measured by tonic skin conductance and self-reports of tension. Contrary to initial expectations, skin conductance levels were greater in the presence of a friend than in the presence of a stranger and greater than in a condition where Ss watched the film alone. The results also showed that a friend who was blocked from view produced higher levels of skin conductance and subjective tension than did a friend who was visible to the S, whereas the effect was just the opposite for visible and nonvisible strangers. Both sets of findings were interpreted in terms of conflicting needs for anonymity and emotional comparison.

Formalizations of Commonsense Psychology

■ The central challenge in commonsense knowledge representation research is to develop content theories that achieve a high degree of both competency and coverage. We describe a new methodology for constructing formal theories in commonsense knowledge domains that complements traditional knowledge representation approaches by first addressing issues of coverage. We show how a close examination of a very general task (strategic planning) leads to a catalog of the concepts and facts that must be encoded for general commonsense reasoning. These concepts are sorted into a manageable number of coherent domains, one of which is the representational area of commonsense human memory. We then elaborate on these concepts using textual corpus-analysis techniques, where the conceptual distinctions made in natural language are used to improve the definitions of the concepts that should be expressible in our formal theories. These representational areas are then analyzed using more traditional knowledge representation techniques, as demonstrated in this article by our treatment of commonsense human memory.

Deja Vu: a knowledge-rich interface for retrieval in digital libraries

Providing access to digital libraries will require interfaces that effectively mediate between the retrieval needs of library users and the materials that the library has to offer. This paper describes Deja Vu, a new interface for retrieval in digital libraries. Rather than relying on traditional querybased techniques, Deja Vu allows users to browse through the subject terms used to catalog library materials to find ones that meet their particular retrieval needs. The browsing process is facilitated by a new knowledge structure introduced in this paper called Expectation Packages. Expectation Packages group together subject terms based on the commonsense knowledge of library users to provide a richly interconnected browsing space. An example application of Deja Vu is described, which incorporates the Library of Congress Thesaurus for Graphic Materials to provide access to online image collections.

Processing Narratives Concerning Protected Values: A Cross-Cultural Investigation of Neural Correlates

Abstract Narratives are an important component of culture and play a central role in transmitting social values. Little is known, however, about how the brain of a listener/reader processes narratives. A receivers response to narration is influenced by the narrators framing and appeal to values. Narratives that appeal to “protected values,” including core personal, national, or religious values, may be particularly effective at influencing receivers. Protected values resist compromise and are tied with identity, affective value, moral decision‐making, and other aspects of social cognition. Here, we investigated the neural mechanisms underlying reactions to protected values in narratives. During fMRI scanning, we presented 78 American, Chinese, and Iranian participants with real‐life stories distilled from a corpus of over 20 million weblogs. Reading these stories engaged the posterior medial, medial prefrontal, and temporo‐parietal cortices. When participants believed that the protagonist was appealing to a protected value, signal in these regions was increased compared with when no protected value was perceived, possibly reflecting the intensive and iterative search required to process this material. The effect strength also varied across groups, potentially reflecting cultural differences in the degree of concern for protected values.