Breck Baldwin

Learn More
Cross-document coreference occurs when the same person, place, event, or concept is discussed in more than one text source. Computer recognition of this phenomenon is important because it helps break "the document boundary" by allowing a user to examine information about a particular entity from multiple text sources at the same time. In this paper we(More)
This paper concerns relationships among focus of attention, choice of referring expression, and perceived coherence of utterances within a discourse segment. It presents a framework and initial theory of centering which are intended to model the local component of attentional state. The paper examines interactions between local coherence and choice of(More)
MAXIMUM ENTROPY MODELS FOR NATURAL LANGUAGE AMBIGUITY RESOLUTION Adwait Ratnaparkhi Supervisor: Professor Mitch Marcus This thesis demonstrates that several important kinds of natural language ambiguities can be resolved to state-of-the-art accuracies using a single statistical modeling technique based on the principle of maximum entropy. We discuss the(More)
Complexity of Lexical Descriptions and its Relevance to Partial Parsing Srinivas Bangalore Supervisor: Aravind K. Joshi In this dissertation, we have proposed novel methods for robust parsing that integrate the exibility of linguistically motivated lexical descriptions with the robustness of statistical techniques. Our thesis is that the computation of(More)
\Ve developed a query-sensitive text summarization technology \Vell suited for the task of determining whether a. document is relevant to <'-" query. Enoug;h of the docurnent is displayed for the user to determine whether the document should l:H~ read in its entirety. Evaluations indicate that sununarics are classif-ied for relevauce uearly as well as(More)
We have developed cross document event tracking technology that extends our earlier efforts in cross document person coreference. The software takes class of events, like "resignations" and clusters documents tha t mention resignations into equivalence classes. Documents belong to the same equivalence class if they mention the same "resignation" event, i.e.(More)
This paper presents a high precision pronoun resolution system that is capable of greater than 90% precision with 60% and better recall for some pronouns. It is suggested that the system is resolving a sub-set of anaphors that do not require general world knowledge for successful resolution. The system does this by being very sensitive to ambiguity, and(More)
Scoring the performance of a system is an extremely important aspect of coreference algorithm performance. The score for a particular run is the single strongest measure of how well the system is performing and it can strongly determine directions for further improvements. In this paper, we present several di erent scoring algorithms and detail their(More)