Googling answers’ models in question-focused summarisation∗
نویسندگان
چکیده
This paper describes the techniques used for our system participating in the Document Understanding Conference 2006. We describe a new system, built from scratch, that focuses primarily on collecting models of possible answers for each question from the Internet, and applying those models to select the answer sentences from the documents in the collection. The system performed averagely in the manual evaluation done by NIST.
منابع مشابه
Macquarie University at BioASQ 5b -- Query-based Summarisation Techniques for Selecting the Ideal Answers
Macquarie University’s contribution to the BioASQ challenge (Task 5b Phase B) focused on the use of query-based extractive summarisation techniques for the generation of the ideal answers. Four runs were submitted, with approaches ranging from a trivial system that selected the first n snippets, to the use of deep learning approaches under a regression framework. Our experiments and the ROUGE r...
متن کاملMacquarie University at BioASQ 5b -- Query-based Summarisation Techniques for Selecting the Ideal Answers
Macquarie University’s contribution to the BioASQ challenge (Task 5b Phase B) focused on the use of query-based extractive summarisation techniques for the generation of the ideal answers. Four runs were submitted, with approaches ranging from a trivial system that selected the first n snippets, to the use of deep learning approaches under a regression framework. Our experiments and the ROUGE r...
متن کاملUnsupervised Biographical Event Extraction Using Wikipedia Traffic
Biographical summarisation can provide succinct and meaningful answers to the question “Who is X?”. Current supervised summarisation approaches extract sentences from documents using features from textual context. In this paper, we explore a novel approach to biographical summarisation, by extracting important sentences from an entity’s Wikipedia page based on internet traffic to the page over ...
متن کاملMacquarie University at BioASQ 5b - Query-based Summarisation Techniques for Selecting the Ideal Answers
Macquarie University’s contribution to the BioASQ challenge (Task 5b Phase B) focused on the use of query-based extractive summarisation techniques for the generation of the ideal answers. Four runs were submitted, with approaches ranging from a trivial system that selected the first n snippets, to the use of deep learning approaches under a regression framework. Our experiments and the ROUGE r...
متن کاملAn Approach for Query-Focused Text Summarisation for Evidence Based Medicine
We present an approach for extractive, query-focused, singledocument summarisation of medical text. Our approach utilises a combination of target-sentence-specific and target-sentence-independent statistics derived from a corpus specialised for summarisation in the medical domain. We incorporate domain knowledge via the application of multiple domain-specific features, and we customise the answ...
متن کامل