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

DBpedia @ Google Summer of Code – GSoC 2017 ( 2017-03-13T11:12:50+01:00 Christopher Schulz)

2017-03-13T11:12:50+01:00 Christopher Schulz

DBpedia, one of InfAI’s community projects, will be part of the 5th Google Summer of Code program. The GsoC has the goal to bring students from all over the globe into open source software development. Read more about "DBpedia @ Google Summer of Code – GSoC 2017"

New GERBIL release v1.2.5 – Benchmarking entity annotation systems ( 2017-03-10T11:49:51+01:00 by Ricardo Usbeck)

2017-03-10T11:49:51+01:00 by Ricardo Usbeck

Dear all, the Smart Data Management competence center at AKSW is happy to announce GERBIL 1.2.5. Read more about "New GERBIL release v1.2.5 – Benchmarking entity annotation systems"

DBpedia Open Text Extraction Challenge – TextExt ( 2017-03-09T12:15:57+01:00 Christopher Schulz)

2017-03-09T12:15:57+01:00 Christopher Schulz

DBpedia, a community project affiliated with the Institute for Applied Informatics (InfAI) e.V., extract structured information from Wikipedia & Wikidata. Now DBpedia started the DBpedia Open Text Extraction Challenge – TextExt. Read more about "DBpedia Open Text Extraction Challenge – TextExt"

The USPTO Linked Patent Dataset release ( 2017-02-24T17:18:51+01:00 by Mofeed Hassan)

2017-02-24T17:18:51+01:00 by Mofeed Hassan

Dear all, We are happy to announce USPTO Linked Patent Dataset release. Patents are widely used to protect intellectual property and a measure of innovation output. Read more about "The USPTO Linked Patent Dataset release"

Two accepted papers in ESWC 2017 ( 2017-02-22T17:43:38+01:00 by Dr. Mohamed Ahmed Sherif)

2017-02-22T17:43:38+01:00 by Dr. Mohamed Ahmed Sherif

Hello Community! We are very pleased to announce the acceptance of two papers in ESWC 2017 research track. The ESWC 2017 is to be held in Portoroz, Slovenia from 28th of May to the 1st of June. Read more about "Two accepted papers in ESWC 2017"