Project QUOTE

In many kinds of prose texts, both literary or newswire texts, reported speech plays an important role as a source of information about characters, their attitudes, and their relationships. In this project, we develop joint inference methods to model the various aspects of reported speech (who is the speaker? the hearer? What is thecontent? What is the relationship between speaker and hearer?) together instead of individually. 

In many kinds of prose texts, both literary or newswire texts, reported speech plays an important role as a source of information about characters, their attitudes, and their relationships. Going further,such information can aid in the analysis of patterns of behavior and the construction of social networks.While readers do not have any problem in assembling representations for complete situations from individual instances of reported speech, thisis still a challenging task for computers. Current state of the artmethods are generally organized as "pipelines" which start from individual instances of reported speech and proceed incrementally tomore global properties of the situation or characters. Since individual instances of reported speech are often short and uninformative, apipeline procedure often causes prediction errors which cannot be rectified in retrospect.In this project, we develop joint inference methods to model the various aspects of reported speech (who is the speaker? the hearer? What is thecontent? What is the relationship between speaker and hearer?) together instead of individually. The resulting joint model takes account of the interdependencies between these aspects. Thus, information from the different aspects can complement each other. The result of this part ofthe project is a solid starting place (in terms of natural language processing methods) for the application of such methods for the automatic analysis of reported speech in digital humanities and social sciences.

Sean Papay