Summarizing Answers for Complicated Questions
نویسندگان
چکیده
This paper describes the multi-document summarization system designed by the Webclopedia team from ISI for DUC 2005. In contrast to the past DUCs and previous designs, this version of our summarizer consists of a query-interpretation component that directly analyzes the given user profile and topic narrative for each document cluster before creating a corresponding summary. This system ranks 4 th on ROUGE-1, 7 th on ROUGE-2 and ROUGE-SU4. Evaluations conducted by Basis Elements show this system ranks 6 th among 32 automatic systems.
منابع مشابه
Understanding and Summarizing Answers in Community-Based Question Answering Services
Community-based question answering (cQA) services have accumulated millions of questions and their answers over time. In the process of accumulation, cQA services assume that questions always have unique best answers. However, with an indepth analysis of questions and answers on cQA services, we find that the assumption cannot be true. According to the analysis, at least 78% of the cQA best ans...
متن کاملOpen domain real-time question answering based on asynchronous multiperspective context-driven retrieval and neural paraphrasing
The live-QA task involves real user questions, extracted from the stream of most recent questions submitted to the Yahoo Answers (YA) site that has not yet been answered. There are two tracks in the live-QA task, general domain, and medical domain. In general domain, unanswered questions are taken from six categories of real-time yahoo question answering feed, and for the medical domain, they a...
متن کاملAnalyzing Users’ Health Information Needs Based on the Yahoo Answers®
Background and Aim: People refer to virtual information resources for answering their medical questions. One of these resources includes question and answering (Q&A) sites in medicine. This study aims to analyze health questions posted on the Yahoo Answers to identify health information needs, the motivations for asking questions, evaluation of information user satisfaction resulted from recei...
متن کاملSummarizing Relevant Information for Question-Answering Using Hybrid Relevance Analysis and Surface Feature Salience
Much research for question-answering aims to answer factoid, definitional and biographical questions. In most cases, the answers are given as a name, date, quantity, and so on. In this paper, we try to merge techniques of multidocument summarization and question-answering to generate a brief, well-organized fluent summary to provide more relevant information for the purpose of answering real-wo...
متن کاملInvestigating the Effect of Changing Answers in Multiple-Choice Questions of Reading and Listening Tests in EFL Context
This study investigates whether the practice of answer changing on multiple-choice questions (MCQs) is beneficial for Iranian students’ overall test performance in EFL context. Several studies have shown that answer changing in multiple choice examinations is generally beneficial for improving scores. On the other hand, some studies have indicated that answer changing in multiple choice examina...
متن کامل