No abstract

No abstract

Open-Domain Question Answering systems (QA) performs the task of detecting text fragments in a collection of documents that contain the response to user's queries. These systems use high complexity tools that reduce its applicability to the treatment of small amounts of text. Consequently, when working on large document collections, QA systems apply Information Retrieval (IR) techniques to reduce drastically text collections to a tractable quantity of relevant text. In this paper, we propose a novel Passage Retrieval (PR) model that performs this task with better performance for QA purposes than current best IR systems 2 Backgrounds in Question Answering and Passage Retrieval 2.1 Information Retrieval and Passage Retrieval

No abstract

No abstract