Selectively Using Linguistic Resources throughout the Question Answering Pipeline
نویسندگان
چکیده
It is generally believed that question answering can benefit from natural language processing methods. So far, however, there have been few systematic studies of this conjecture. We report on ongoing work that is aimed at understanding the contribution of linguistically informed modules and resources to the overall performance of a generic question answering system. Specifically, we describe the ways in which currently we use linguistically motivated techniques, and demonstrate the impact of integrating, or not integrating, these techniques on the overall performance of our question answering system. Evaluation results are based on the TREC 2002 and TREC 2003 question sets.
منابع مشابه
Selectively Using Relations to Improve Precision in Question Answering
Despite the intuition that linguistically sophisticated techniques should be beneficial to question answering, real gains in performance have yet to be demonstrated empirically in a reliable manner. Systems built around sophisticated linguistic analysis generally perform worse than their linguistically-uninformed cousins. We believe that the key to effective application of natural language proc...
متن کاملAnswer Selection in a Multi-stream Open Domain Question Answering System
Question answering systems aim to meet users’ information needs by returning exact answers in response to a question. Traditional open domain question answering systems are built around a single pipeline architecture. In an attempt to exploit multiple resources as well as multiple answering strategies, systems based on a multi-stream architecture have recently been introduced. Such systems face...
متن کاملItalian Language Resources in a Question Answering Task
The paper describes the first phase of a work dedicated to the exploitation of linguistic resources in a QA application for Italian. In particular, the form of Italian Wh-questions introduced by Quale and Che is analyzed, in order to highlight the information that is crucial for singling out the answer(s) in a document collection. A preliminar investigation of the modalities of linguistic resou...
متن کاملIhardetsi: A Question Answering system for Basque built on reused linguistic processors
This paper presents Ihardetsi, a question answering system oriented to Basque. We describe the main architecture of the system, paying special attention to the use of linguistic resources and tools. The system has been built reusing such tools, on the basis that general linguistic processors can be adapted to satisfy the requirements of the question answering task. This methodology can be suita...
متن کاملAn Analysis of Question Processing of English and Chinese for the NTCIR 5 Cross-Language Question Answering Task
An important element in question answering systems is the analysis and interpretation of questions. Using the NTCIR 5 Cross-Language Question Answering (CLQA) question test set we demonstrate that the accuracy of deep question analysis is dependent on the quantity and suitability of the available linguistic resources. We further demonstrate that applying question analysis tools developed on mon...
متن کامل