Accession Number : AD1004699


Title :   ADAPT.DCU at TREC LiveQA: A Sentence Retrieval based Approach to Live Question Answering


Descriptive Note : Conference Paper


Corporate Author : Dublin City University Dublin Ireland


Personal Author(s) : Bogdanova,Dasha ; Ganguly,Debasis ; Foster,Jennifer ; Vahid,Ali H


Full Text : https://apps.dtic.mil/dtic/tr/fulltext/u2/1004699.pdf


Report Date : 20 Nov 2015


Pagination or Media Count : 7


Abstract : This paper describes the work done by ADAPT centre at Dublin City University towards automatically answering questions for the TREC LiveQA track. The system is based on a sentence retrieval approach. In particular, we first use the title of a new question as a query so as to retrieve a ranked list of conceptually similar questions from an index of previously asked on Yahoo! Answers. We then extract the best matching sentences from the answers of the retrieved questions. In order to construct the final answer, we combine these sentences with the best answer of the top ranked (most similar to the query) question. When no pre-existing questions with sufficient similarity with the new one can be retrieved from the index, we output an answer from a candidate set of pre-generated answers based on the domain of the question.


Distribution Statement : APPROVED FOR PUBLIC RELEASE