Using a Text Summarization System for Monolingual Question Answering
نویسندگان
چکیده
In this paper, we present and analyze the results of the application of a text summarization system – GistSumm – to the task of monolingual question answering at CLEF 2006 for Portuguese texts. Using the system ability to produce topic-oriented summaries, we aimed at assessing its accuracy in finding answers to the posted questions, which were used as the topics for producing the corresponding summaries. The obtained results were very poor, indicating that simple summarization techniques alone are not enough for question answering.
منابع مشابه
Experiments on Applying a Text Summarization System for Question Answering
In this paper, we present and analyze the results of the application of a text summarization system – GistSumm – to the task of monolingual question answering at CLEF 2006 for Portuguese texts. We hypothesized that topicoriented summarization techniques could be able to produce more accurate answers. However, our results showed that there is a big gap to be overcome for summarization to be dire...
متن کاملQuery-Biased Text Summarization as a Question-Answering Technique
these are discussed in Section 3). Segments with strong Text summarization may soon become a competitive method of answering queries asked of large text corpora. A query brings up a set of documents. These documents are then filtered by a summarizer: it constructs brief summaries from document fragments conceptually close to the query terms. We present the implementation of such a summarization...
متن کاملExamining the Role of Statistical and Linguistic Knowledge Sources in a General-Knowledge Question-Answering System
We describe and evaluate an implemented system for general-knowledge question answering. The system combines techniques for standard ad-hoc information retrieval (IR), query-dependent text summarization, and shallow syntactic and semantic sentence analysis. In a series of experiments we examine the role of each statistical and linguistic knowledge source in the question-answering system. In con...
متن کاملAnnotating a parallel monolingual treebank with semantic similarity relations
We describe an ongoing effort to build a large-scale parallel and comparable monolingual treebank for Dutch of 1 million words, where nodes of dependency trees are aligned and labeled according to a limited set of semantic similarity relations. We address alignment of sentences and dependency trees, both manual and automatic. We introduce new annotation tools, present results from pilot experim...
متن کاملAnnotating a parallel monolingual treebank with semantic similarity relations
We describe an ongoing effort to build a large-scale parallel/comparable monolingual treebank for Dutch of 1 million words, where nodes of dependency trees are aligned and labeled according to a limited set of semantic similarity relations. We address alignment of sentences and dependency trees, both manual and automatic. We introduce new annotation tools, present results from pilot experiments...
متن کامل