HAWK: Hybrid Question Answering over Linked Data

HAWK is going to drive forth the OKBQA vision of hybrid question answering using Linked Data and full-text information. Performance benchmarks are done on the QALD-4 task 3 hybrid.

Source Code Demo Issues

Introduction

Recent advances in question answering (QA) over Linked Data provide end users with more and more sophisticated tools for querying linked data by expressing their information need in natural language. This allows access to the wealth of structured data available on the Semantic Web also to non-experts. However, a lot of information is still available only in textual form, both on the Document Web and in the form of labels and abstracts in Linked Data sources. Therefore, a considerable number of questions can only be answered by using hybrid question answering approaches, which can find and combine information stored in both structured and textual data sources.

Architecture

The HAWK Architecture

We present HAWK, the (to best of our knowledge) first full-fledged hybrid QA framework for entity search over Linked Data and textual data.

Given an input query, HAWK implements an 8-step pipeline, which comprises 1) part-of-speech tagging, 2) detecting entities in the query, 3) dependency parsing and 4) applying linguistic pruning heuristics for an in-depth analysis of the natural language input. The results of these first four steps is a predicate-argument graph annotated with resources from the Linked Data Web. HAWK then 5) assign semantic meaning to nodes and 6) generates basic triple patterns for each component of the input query with respect to a multitude of features. This deductive linking of triples results in a set of SPARQL queries containing text operators as well as triple patterns. In order to reduce operational costs, 7) HAWK discards queries using several rules, e.g., by discarding not connected query graphs. Finally, 8) queries are ranked using extensible feature vectors and cosine similarity.

Supplementary material concerning the evaluation and implementation of HAWK can be found here

Project Team

Publications

by (Editors: ) [BibTex of ]

News

Jekyll RDF Tutorial Screencast ( 2018-08-07T11:11:12+02:00 by Natanael Arndt)

2018-08-07T11:11:12+02:00 by Natanael Arndt

Since 2016 we are developing Jekyll-RDF a plugin for the famous Jekyll–static website generator. Read more about "Jekyll RDF Tutorial Screencast"

DBpedia Day @ SEMANTiCS 2018 ( 2018-07-20T14:37:25+02:00 by Johannes Frey)

2018-07-20T14:37:25+02:00 by Johannes Frey

Don’t miss the 12th edition of the DBpedia Community Meeting in Vienna, the city with the highest quality of life in the world. Read more about "DBpedia Day @ SEMANTiCS 2018"

SANSA 0.4 (Semantic Analytics Stack) Released ( 2018-06-26T18:33:38+02:00 by Prof. Dr. Jens Lehmann)

2018-06-26T18:33:38+02:00 by Prof. Dr. Jens Lehmann

We are happy to announce SANSA 0.4 – the fourth release of the Scalable Semantic Analytics Stack. Read more about "SANSA 0.4 (Semantic Analytics Stack) Released"

AKSW is organizing the 6th Leipzig Semantic Web Day (LSWT2018) ( 2018-04-17T14:14:17+02:00 by Natanael Arndt)

2018-04-17T14:14:17+02:00 by Natanael Arndt

On June 18th 2018 we will have the 6th Leipzig Semantic Web Day (LSWT2018). A platform for regional actors to get in touch with each other regarding Semantic Web topics. Read more about "AKSW is organizing the 6th Leipzig Semantic Web Day (LSWT2018)"

SANSA 0.3 (Semantic Analytics Stack) Released ( 2017-12-18T11:15:38+01:00 by Simon Bin)

2017-12-18T11:15:38+01:00 by Simon Bin

Dear all, We are happy to announce SANSA 0.3 – the third release of the Scalable Semantic Analytics Stack. Read more about "SANSA 0.3 (Semantic Analytics Stack) Released"