Earl J. Wagner

Compare&contrast: using the web to discover comparable cases for news stories

Comparing and contrasting is an important strategy people employ to understand new situations and create solutions for new problems. Similar events can provide hints for problem solving, as well as larger contexts for understanding the specific circumstances of an event. Lessons can leaned from past experience, insights can be gained about the new situation from familiar examples, and trends can be discovered among similar events. As the largest knowledge base for human beings, the Web provides both an opportunity and a challenge to discover comparable cases in order to facilitate situation analysis and problem solving. In this paper, we present Compare & Contrast, a system that uses the Web to discover comparable cases for news stories, documents about similar situations but involving distinct entities. The system analyzes a news story given by the user and builds a model of the story. With the story model, the system dynamically discovers entities comparable to the main entity in the original story and uses these comparable entities as seeds to retrieve web pages about comparable cases. The system is domain independent, does not require any domain-specific knowledge engineering efforts, and deals with the complexity of unstructured text and noise on the web in a robust way. We evaluated the system with an experiment on a collection of news articles and a user study.

Rich interfaces for reading news on the web

Using content-specific models to guide information retrieval and extraction can provide richer interfaces to end-users for both understanding the context of news events and navigating related news articles. In this paper we discuss a system, Brussell, that uses semantic models to organize retrieval and extraction results, generating both storylines explaining how news event situations unfold and also biographical sketches of the situation participants. We generalize these models to introduce a new category of knowledge representation, an explanatory structure, that can scale up to include information from hundreds of documents, yet still provide model-based UI support to end-users. An informal survey of business news suggests the broad prevalence of news event situations indicating Brussells potential utility, while an evaluation quantifies its performance in finding kidnapping situations.

Modeling multiple-event situations across news articles

Readers interested in the context of an event covered in the news such as the dismissal of a lawsuit can benefit from easily finding out about the overall news situation, the legal trial, of which the event is a part. Guided by abstract models of news situation types such as legal trials, corporate acquisitions, and kidnappings, Brussell is a system that presents situation instances it creates by reading multiple articles about the specific events that comprise them. We discuss how these situation models are structured and how they drive the creation of particular instances.