Cons ide ra t i on of the s i m i l a r i t y between d i rec t and ind i rec t speech act unders tand ing g ive r i s e to the notion that taxonomies of speech acts may not be he lp fu l in modell ing language understanding. A computer model which t reats represent a t i o n s o f d i r e c t and i n d i r e c t speech acts s i m i l a r l y and succesful ly has been implemented without any su...

For natural language understanding researchers at PRC, preparing for MUC-3 was a usefu l endeavor in many respects . The value of having a well-defined task, a large corpus, and a n automated scoring program can hardly be overestimated . This exercise has pointed out the strengths of our system, confirmed our feelings about which aspects most need work, and taugh t us how to approach a task of ...

In this paper, we present an extension of the DCR method, which is a framework for the deep evaluation of Spoken Language Understanding (SLU) Systems. The key point of our contribution is the use of a linguistic typology in order to generate an evaluation corpus that covers a significant number of the linguistic phenomena we want to evaluate our system on. This allows to have more objective and...

This paper describes UAIC’s Question Answering for Machine Reading Evaluation systems participating in the QA4MRE 2011 evaluation task. The system is designed to extract knowledge from large volumes of text and to use this knowledge to answer questions in Romanian and English monolingual tasks. Our systems were built on the architecture of a Question Answering system, customized for this new ta...

The temporal interpretation of events is crucial to many applications of natural language understanding. Interpreting events as described in individual utterances and discourse requires both semantic and pragmatic processing. We develop representations for events that reflect the internal structure of different situation types. We propose semantic constraints through which the representations o...

Introduction Much sponsored research in our lab either falls under or intersects with machine reading. In this short paper we give an encapsulated presentation of some of the research in question, leaving aside, for the most part, the considerable detailed technical information that underlies our work. Demonstrations of our technology will be provided at the symposium itself. Our machine readin...

Linguistics studies have shown that action verbs often denote some Change of State (CoS) as the result of an action. However, the causality of action verbs and its potential connection with the physical world has not been systematically explored. To address this limitation, this paper presents a study on physical causality of action verbs and their implied changes in the physical world. We firs...

In this paper criticality within a voting game is rigorously defined and examined. Criticality forms the basis of the traditional voting power measures frequently employed to analyse voting games; therefore understanding criticality is a pre-requisite to understanding any such analysis. The concept of criticality is extended to encompass games in which players are allowed to express multiple le...

The statistical significance of the results of the MUC-5 evaluation is determined using a computer-intensiv e method of hypothesis testing known as approximate randomization . The exact method is described in detail in 111 an d [2] and has been used as the accepted statistical test for the MUC results since MUC-3 . The purpose of the statistica l testing is to determine whether the scores of th...

As part of our TIPSTER III research program, we have continued our research into strategies to resolve coreferences within a free text document; this research was begun during our TIPSTER II research program. In the TIPSTER II Proceedings paper, "An Evaluation of Coreference Resolution Strategies for Acquiring Associated Information," the goal was to evaluate the contributions of various techni...