Capturing Knowledge in Semantically-typed Relational Patterns to Enhance Relation Linking

Singh, K. M.; Mulang, Isaiah Onando; Lytra, Ioanna; Jaradeh, Mohamad Yaser; Sakor, Ahmad; Vidal, María-Esther; Lange, Christoph; Auer, Sören

doi:10.1145/3148011.3148031

Cited by 17 publications

(15 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ReMatch [14] 0.12 0.31 RelMatch [20] 0.15 0.29 EARL without adaptive learning 0.32 0.45 EARL with adaptive learning 0.36 0.47 Table 6. Evaluating EARL's Relation Linking performance…”

Section: Systemmentioning

confidence: 99%

See 1 more Smart Citation

EARL: Joint Entity and Relation Linking for Question Answering over Knowledge Graphs

Dubey

Banerjee

Chaudhuri

et al. 2018

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Many question answering systems over knowledge graphs rely on entity and relation linking components in order to connect the natural language input to the underlying knowledge graph. Traditionally, entity linking and relation linking have been performed either as dependent sequential tasks or as independent parallel tasks. In this paper, we propose a framework called EARL, which performs entity linking and relation linking as a joint task. EARL implements two different solution strategies for which we provide a comparative analysis in this paper: The first strategy is a formalisation of the joint entity and relation linking tasks as an instance of the Generalised Travelling Salesman Problem (GTSP). In order to be computationally feasible, we employ approximate GTSP solvers. The second strategy uses machine learning in order to exploit the connection density between nodes in the knowledge graph. It relies on three base features and re-ranking steps in order to predict entities and relations. We compare the strategies and evaluate them on a dataset with 5000 questions. Both strategies significantly outperform the current state-of-the-art approaches for entity and relation linking.

show abstract

“…ReMatch [14] 0.12 0.31 RelMatch [20] 0.15 0.29 EARL without adaptive learning 0.32 0.45 EARL with adaptive learning 0.36 0.47 Table 6. Evaluating EARL's Relation Linking performance…”

Section: Systemmentioning

confidence: 99%

“…Word embedding models are also frequently used to overcome the linguistic gap for relation linking. RelMatch [20] improves the accuracy of the PATTY dataset for relation linking. There are tools such as ReMatch [14] which uses wordnet similarity for relation linking.…”

Section: Related Workmentioning

confidence: 99%

EARL: Joint Entity and Relation Linking for Question Answering over Knowledge Graphs

Dubey

Banerjee

Chaudhuri

et al. 2018

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…All experiments were executed on 10 virtual servers, each with 8 cores, 32 GB RAM and the Ubuntu 16.04.3 operating system. It took us 22 days to generate training data by executing questions of considered datasets for all 28 components, as some tools such as ReMatch [20] and RelationMatcher [27] took approximately 120 and 30 seconds, respectively, to process each question.…”

Section: Corpus Creationmentioning

confidence: 99%

“…We prepared two separate datasets from LC-QuAD and QALD. We adopted the methodology presented in [6] and [27] for the benchmark creation of the subsequent steps of the QA pipelines. Furthermore, the accuracy metrics are micro F-Score (F-Score) as a harmonic mean of micro precision and micro recall.…”

Section: Preparing Training Datasetsmentioning

confidence: 99%

Why Reinvent the Wheel

Singh

Radhakrishna

Both

et al. 2018

Proceedings of the 2018 World Wide Web Conference on World Wide Web - WWW '18

Self Cite

View full text Add to dashboard Cite

Modern question answering (QA) systems need to flexibly integrate a number of components specialised to fulfil specific tasks in a QA pipeline. Key QA tasks include Named Entity Recognition and Disambiguation, Relation Extraction, and Query Building. Since a number of different software components exist that implement different strategies for each of these tasks, it is a major challenge to select and combine the most suitable components into a QA system, given the characteristics of a question. We study this optimisation problem and train classifiers, which take features of a question as input and have the goal of optimising the selection of QA components based on those features. We then devise a greedy algorithm to identify the pipelines that include the suitable components and can effectively answer the given question. We implement this model within Frankenstein, a QA framework able to select QA components and compose QA pipelines. We evaluate This paper is published under the Creative Commons Attribution 4.0 International (CC BY 4.0) license. Authors reserve their rights to disseminate the work on their personal and corporate Web sites with the appropriate attribution.

show abstract

“…For each of the QB components, given a correct set of URIs as input, the generated SPARQL query is compared to the benchmark SPARQL query for the given question by comparing the answers the SPARQL queries retrieve from DBpedia. A similar component benchmarking procedure has been followed in [23,32].…”

Section: Component Benchmarkingmentioning

confidence: 99%

No One is Perfect: Analysing the Performance of Question Answering Components over the DBpedia Knowledge Graph

Singh¹,

Lytra²,

Radhakrishna³

et al. 2018

Preprint

Self Cite

View full text Add to dashboard Cite

Question answering (QA) over knowledge graphs has gained significant momentum over the past five years due to the increasing availability of large knowledge graphs and the rising importance of question answering for user interaction. DBpedia has been the most prominently used knowledge graph in this setting and most approaches currently use a pipeline of processing steps connecting a sequence of components. In this article, we analyse and micro evaluate the behaviour of 29 available QA components for the DBpedia knowledge graph that were released by the research community since 2010. As a result, we provide a perspective on collective failure cases, suggest characteristics of QA components that prevent them from performing better and provide future challenges and research directions in the field.

show abstract

Capturing Knowledge in Semantically-typed Relational Patterns to Enhance Relation Linking

Cited by 17 publications

References 12 publications

EARL: Joint Entity and Relation Linking for Question Answering over Knowledge Graphs

EARL: Joint Entity and Relation Linking for Question Answering over Knowledge Graphs

Why Reinvent the Wheel

No One is Perfect: Analysing the Performance of Question Answering Components over the DBpedia Knowledge Graph

Contact Info

Product

Resources

About