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

SML-Bench 0.2 Released ( 2017-05-11T13:01:45+02:00 by Patrick Westphal)

2017-05-11T13:01:45+02:00 by Patrick Westphal

Dear all, we are happy to announce the 0.2 release of SML-Bench, our Structured Machine Learning benchmark framework. SML-Bench provides full benchmarking scenarios for inductive supervised machine learning covering different knowledge representation languages like OWL and Prolog. Read more about "SML-Bench 0.2 Released"

AKSW Colloquium, 08.05.2017, Scalable RDF Graph Pattern Matching ( 2017-05-08T09:42:49+02:00 by Lorenz Bühmann)

2017-05-08T09:42:49+02:00 by Lorenz Bühmann

At the AKSW Colloquium, on Monday 8th of May 2017, 3 PM, Lorenz Bühmann will discuss a paper titled “Type-based Semantic Optimization for Scalable RDF Graph Pattern Matching” of Kim et al. Read more about "AKSW Colloquium, 08.05.2017, Scalable RDF Graph Pattern Matching"

ESWC 2017 accepted two Demo Papers by AKSW members ( 2017-04-19T10:19:43+02:00 Christopher Schulz)

2017-04-19T10:19:43+02:00 Christopher Schulz

Hello Community! The 14th ESWC, which takes place from May 28th to June 1st 2017 in Portoroz, Slovenia, accepted two demos to be presented at the conference. Read more about them in the following:                                                                         1. Read more about "ESWC 2017 accepted two Demo Papers by AKSW members"

AKSW Colloquium, 10.04.2017, GeoSPARQL on geospatial databases ( 2017-04-07T10:43:55+02:00 by Dr. Matthias Wauer)

2017-04-07T10:43:55+02:00 by Dr. Matthias Wauer

At the AKSW Colloquium, on Monday 10th of April 2017, 3 PM, Matthias Wauer will discuss a paper titled “Ontop of Geospatial Databases“. Read more about "AKSW Colloquium, 10.04.2017, GeoSPARQL on geospatial databases"

AKSW Colloquium, 03.04.2017, RDF Rule Mining ( 2017-03-31T13:39:28+02:00 TommasoSoru)

2017-03-31T13:39:28+02:00 TommasoSoru

At the AKSW Colloquium, on Monday 3rd of April 2017, 3 PM, Tommaso Soru will present the state of his ongoing research titled “Efficient Rule Mining on RDF Data”, where he will introduce Horn Concerto, a novel scalable SPARQL-based approach … Continue reading → Read more about "AKSW Colloquium, 03.04.2017, RDF Rule Mining"