Description of SQUASH, the SFU Question Answering Summary Handler for the DUC-2005 Summarization Task
نویسندگان
چکیده
This paper describes the design of the SQUASH system, the SFU Question Answering Summary Handler, developed by members of the Natural Language Lab from the SFU School of Computing Science in order to participate in the 2005 Document Understanding Conference (DUC-2005) summarization task. The system design involves semantic role labelling, semantic subgraph-based sentence selection and automatic post-editing to create a question-based 250 word summary from a set of documents, all of which are relevant to the question topic. We also present and discuss the various evaluations performed on our system output, comparing our performance to the other systems that took part in the DUC 2005 competition.
منابع مشابه
Description of SQUASH, the SFU Question Answering Summary Handler for the DUC-2006 Summarization Task
This paper describes the design of the SQUASH system, the SFU Question Answering Summary Handler, developed by members of the Natural Language Lab from the SFU School of Computing Science in order to participate in the 2006 Document Understanding Conference (DUC-2006) summarization task. The SQUASH system for DUC-2006 built upon the SQUASH system that was built for the last year’s DUC-2005 comp...
متن کاملLanguage Model Passage Retrieval for Question-Oriented Multi Docu- ment Summarization
The goal of question-oriented text summarization aims at producing the informative short description according to the given queries. This is somewhat similar to the target of question answering which retrieves exact answers from large raw text collections. In this paper, we present a resource, and training data-free summarization model for DUC multi-document summarization task. Similar as last ...
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 کاملLite - GISTexter at DUC 2005
This paper describes how Language Computer Corporation’s Lite-GISTexter multi-document summarization system addresses the challenge of providing summary-length answers to the types of complex questions asked in DUC 2005. We show that techniques first used in the automatic answering of “relationship” questions can be used in multi-document summarization in order to provide accurate and responsiv...
متن کاملDUC 2005: Evaluation Of Question-Focused Summarization Systems
The Document Understanding Conference (DUC) 2005 evaluation had a single useroriented, question-focused summarization task, which was to synthesize from a set of 25-50 documents a well-organized, fluent answer to a complex question. The evaluation shows that the best summarization systems have difficulty extracting relevant sentences in response to complex questions (as opposed to representativ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2005