TU Darmstadt / ULB / TUbiblio

Evaluation of a Layered Approach to Question Answering over Linked Data

Walter, Sebastian and Unger, Christina and Cimiano, Philipp and Bär, Daniel (2012):
Evaluation of a Layered Approach to Question Answering over Linked Data.
In: Proceedings of the 11th International Semantic Web Conference, Boston, MA, USA, pp. 362-374, [Online-Edition: https://link.springer.com/chapter/10.1007/978-3-642-35173-0_...],
[Conference or Workshop Item]

Abstract

We present a question answering system architecture which processes natural language questions in a pipeline consisting of five steps: i) question parsing and query template generation, ii) lookup in an inverted index, iii) string similarity computation, iv) lookup in a lexical database in order to find synonyms, and v) semantic similarity computation. These steps are ordered with respect to their computational effort, following the idea of layered processing: questions are passed on along the pipeline only if they cannot be answered on the basis of earlier processing steps, thereby invoking computationally expensive operations only for complex queries that require them. In this paper we present an evaluation of the system on the dataset provided by the 2nd Open Challenge on Question Answering over Linked Data (QALD-2). The main, novel contribution is a systematic empirical investigation of the impact of the single processing components on the overall performance of question answering over linked data.

Item Type: Conference or Workshop Item
Erschienen: 2012
Creators: Walter, Sebastian and Unger, Christina and Cimiano, Philipp and Bär, Daniel
Title: Evaluation of a Layered Approach to Question Answering over Linked Data
Language: English
Abstract:

We present a question answering system architecture which processes natural language questions in a pipeline consisting of five steps: i) question parsing and query template generation, ii) lookup in an inverted index, iii) string similarity computation, iv) lookup in a lexical database in order to find synonyms, and v) semantic similarity computation. These steps are ordered with respect to their computational effort, following the idea of layered processing: questions are passed on along the pipeline only if they cannot be answered on the basis of earlier processing steps, thereby invoking computationally expensive operations only for complex queries that require them. In this paper we present an evaluation of the system on the dataset provided by the 2nd Open Challenge on Question Answering over Linked Data (QALD-2). The main, novel contribution is a systematic empirical investigation of the impact of the single processing components on the overall performance of question answering over linked data.

Title of Book: Proceedings of the 11th International Semantic Web Conference
Uncontrolled Keywords: UKP_a_NLP4Wikis;UKP_p_WIKULU;UKP_s_DKPro_Similarity;reviewed
Divisions: 20 Department of Computer Science
20 Department of Computer Science > Ubiquitous Knowledge Processing
Event Location: Boston, MA, USA
Date Deposited: 31 Dec 2016 14:29
Official URL: https://link.springer.com/chapter/10.1007/978-3-642-35173-0_...
Identification Number: TUD-CS-2012-0158
Related URLs:
Export:
Suche nach Titel in: TUfind oder in Google
Send an inquiry Send an inquiry

Options (only for editors)

View Item View Item