Đang chuẩn bị nút TẢI XUỐNG, xin hãy chờ
Tải xuống
In Information Retrieval (IR) in general and Question Answering (QA) in particular, queries and relevant textual content often significantly differ in their properties and are therefore difficult to relate with traditional IR methods, e.g. key-word matching. In this paper we describe an algorithm that addresses this problem, but rather than looking at it on a term matching/term reformulation level, we focus on the syntactic differences between questions and relevant text passages. To this end we propose a novel algorithm that analyzes dependency structures of queries and known relevant text passages and acquires transformational patterns that can be used to. | Answer Sentence Retrieval by Matching Dependency Paths Acquired from Question Answer Sentence Pairs Michael Kaisser AGT Group R D GmbH Jagerstr. 41 10117 Berlin Germany mkaisser@agtgermany.com Abstract In Information Retrieval IR in general and Question Answering QA in particular queries and relevant textual content often significantly differ in their properties and are therefore difficult to relate with traditional IR methods e.g. key-word matching. In this paper we describe an algorithm that addresses this problem but rather than looking at it on a term matching term reformulation level we focus on the syntactic differences between questions and relevant text passages. To this end we propose a novel algorithm that analyzes dependency structures of queries and known relevant text passages and acquires transformational patterns that can be used to retrieve relevant textual content. We evaluate our algorithm in a QA setting and show that it outperforms a baseline that uses only dependency information contained in the questions by 300 and that it also improves performance of a state of the art QA system significantly. 1 Introduction It is a well known problem in Information Retrieval IR and Question Answering QA that queries and relevant textual content often significantly differ in their properties and are therefore difficult to match with traditional IR methods. A common example is a user entering words to describe their information need that do not match the words used in the most relevant indexed documents. This work addresses this problem but shifts focus from words to syntactic structures of questions and relevant pieces of text. To this end we present a novel algorithm that analyses the de pendency structures of known valid answer sentence and from these acquires patterns that can be used to more precisely retrieve relevant text passages from the underlying document collection. To achieve this the position of key phrases in the answer sentence relative to the
