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

Former Members

Publications

by (Editors: ) [BibTex of ]

News

DBpedia Day @ SEMANTiCS 2021 ( 2021-07-30T09:54:45+02:00 by Julia Holze)

2021-07-30T09:54:45+02:00 by Julia Holze

We are happy to announce that we are partnering again with the SEMANTiCS Conference which will host this year’s DBpedia Day on September 9, 2021. Read more about "DBpedia Day @ SEMANTiCS 2021"

LDK Conference meets DBpedia in Zaragoza, Spain ( 2021-07-09T10:37:27+02:00 by Julia Holze)

2021-07-09T10:37:27+02:00 by Julia Holze

We are happy to announce that we will organize a DBpedia Tutorial on September 1, 2021 in Zaragoza, Spain. This DBpedia tutorial will be part of the Language, Data and Knowledge conference 2021. Read more about "LDK Conference meets DBpedia in Zaragoza, Spain"

Assessing Language Identification Over DBpedia ( 2021-05-04T23:27:40+02:00 EdgardMarx)

2021-05-04T23:27:40+02:00 EdgardMarx

Large-scale multilingual knowledge bases (KBs) are the key for cross-lingual and multilingual applications such as Question Answering, Machine  Translation,  and  Search. Read more about "Assessing Language Identification Over DBpedia"

DBpedia Tutorial @ Knowledge Graph Conference 2021 ( 2021-04-09T13:20:50+02:00 by Julia Holze)

2021-04-09T13:20:50+02:00 by Julia Holze

On May 4, 2021 we will organize a tutorial at the Knowledge Graph Conference (KGC) 2021. Read more about "DBpedia Tutorial @ Knowledge Graph Conference 2021"

DBpedia @ Google Summer of Code program 2021 ( 2021-03-15T09:41:22+01:00 by Julia Holze)

2021-03-15T09:41:22+01:00 by Julia Holze

DBpedia, one of InfAI’s community projects, will participate in the Google Summer of Code (GSoC) program for the 10th time. The GsoC program has the goal to bring students from all over the globe into open source software development. Read more about "DBpedia @ Google Summer of Code program 2021"