Data Set Used
This paper presents the current status of work to extend the JAVELIN QA system with domain semantics for question answering in restricted domains. We discuss how the original architecture was extended, and how the system modules must be adjusted to incorporate knowledge from existing ontologies and information provided by third-party annotation tools.
In this paper we describe question answering research being pursued as a joint project between Columbia University and the University of Colorado at Boulder as part of ARDA's AQUAINT program. As a foundation for targeting complex questions involving opinions, events, and paragraph-length answers, we recently built two systems for answering short factual… (More)
We describe our participation in tasks 2, 4 and 5 of the DUC 2004 evaluation. For each task, we present the sys-tem(s) used, focusing on novel and newly developed aspects. We also analyze the results of the human and automatic evaluations.
We present an overview of DefScriber, a system developed at Columbia University that combines knowledge-based and statistical methods to answer definitional questions of the form, " What is X? " We discuss how DefScriber was applied to the definition questions in the TREC 2003 QA track main task. We conclude with an analysis of our system's results on the… (More)
We present DefScriber, a fully implemented system that combines knowledge-based and statistical methods in forming multi-sentence answers to open-ended defi-nitional questions of the form, " What is X? " We show how a set of definitional predicates proposed as the knowledge-based side of our approach can be used to guide the selection of definitional… (More)
Current question answering tasks handle definitional questions by seeking answers which are factual in nature. While factual answers are a very important component in defining entities, a wealth of qualitative data is often ignored. In this incipient work, we define qualitative dimensions (credibility, sentiment, contradictions etc.) for evaluating answers… (More)
We present a technique for reading sentences and producing sets of hypothetical relations that the sentence may be expressing. The technique uses large amounts of instance-level background knowledge about the relations in order to gather statistics on the various ways the relation may be expressed in language, and was inspired by the observation that half… (More)
In this paper, we describe the JAVELIN Cross Language Question Answering system, which includes modules for question analysis, keyword translation, document retrieval, information extraction and answer generation. In the NTCIR6 CLQA2 evaluation, our system achieved 19% and 13% accuracy in the English-to-Chinese and English-to-Japanese subtasks,… (More)