Neural machine translating from natural language to SPARQL

Yin, Xiaoyu; Gromann, Dagmar; Rudolph, Sebastian

doi:10.1016/j.future.2020.12.013

Cited by 47 publications

(50 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Third, there are also other QA approaches which work with neural networks relying on large, templated datasets such as sequence-to-sequence models [24,33]. However, we do not focus on this research direction in this work.…”

Section: Related Workmentioning

confidence: 99%

Knowledge Graph Question Answering Using Graph-Pattern Isomorphism

Vollmers

Jalota

Moussallem

et al. 2021

Studies on the Semantic Web

View full text Add to dashboard Cite

Knowledge Graph Question Answering (KGQA) systems are often based on machine learning algorithms, requiring thousands of question-answer pairs as training examples or natural language processing pipelines that need module fine-tuning. In this paper, we present a novel QA approach, dubbed TeBaQA. Our approach learns to answer questions based on graph isomorphisms from basic graph patterns of SPARQL queries. Learning basic graph patterns is efficient due to the small number of possible patterns. This novel paradigm reduces the amount of training data necessary to achieve state-of-the-art performance. TeBaQA also speeds up the domain adaption process by transforming the QA system development task into a much smaller and easier data compilation task. In our evaluation, TeBaQA achieves state-of-the-art performance on QALD-8 and delivers comparable results on QALD-9 and LC-QuAD v1. Additionally, we performed a fine-grained evaluation on complex queries that deal with aggregation and superlative questions as well as an ablation study, highlighting future research challenges.

show abstract

Section: Related Workmentioning

confidence: 99%

Knowledge Graph Question Answering Using Graph-Pattern Isomorphism

Vollmers

Jalota

Moussallem

et al. 2021

Studies on the Semantic Web

View full text Add to dashboard Cite

show abstract

“…Encoder-decoder architecture of seq2seq models can vary from RNN, CNN based to transformer models. Prior research shows (Yin, Gromann, and Rudolph 2021) that CNN based seq2seq model performs best among these for translating natural language to SPARQL query. Our preliminary experimental results were consistent with this fact since the CNN based model performed the best.…”

Section: Stage-i: Seq2seq Modelmentioning

confidence: 99%

“…Cheng and Lapata (2018) develops a system based on sequence-to-tree model where logic is in the latent form and supervision is in the form of final answer entity. Advances of translating natural language query to structured languages using NMT models (Yin, Gromann, and Rudolph 2021;Cai et al 2017) is emerging in recent years. In case of KGQA task, these NMT based…”

Section: Introductionmentioning

confidence: 99%

Knowledge Graph Question Answering via SPARQL Silhouette Generation

Purkayastha,

Dana,

Garg

et al. 2021

Preprint

View full text Add to dashboard Cite

Knowledge Graph Question Answering (KGQA) has become a prominent area in natural language processing due to the emergence of large-scale Knowledge Graphs (KGs). Recently Neural Machine Translation based approaches are gaining momentum that translates natural language queries to structured query languages thereby solving the KGQA task. However, most of these methods struggle with out-of-vocabulary words where test entities and relations are not seen during training time. In this work, we propose a modular two-stage neural architecture to solve the KGQA task. The first stage generates a sketch of the target SPARQL called SPARQL silhouette for the input question. This comprises of (1) Noise simulator to facilitate out-of-vocabulary words and to reduce vocabulary size (2) seq2seq model for text to SPARQL silhouette generation. The second stage is a Neural Graph Search Module. SPARQL silhouette generated in the first stage is distilled in the second stage by substituting precise relation in the predicted structure. We simulate ideal and realistic scenarios by designing a noise simulator. Experimental results show that the quality of generated SPARQL silhouette in the first stage is outstanding for the ideal scenarios but for realistic scenarios (i.e. noisy linker), the quality of the resulting SPARQL silhouette drops drastically. However, our neural graph search module recovers it considerably. We show that our method can achieve reasonable performance improving the state-of-art by a margin of 3.72% F1 for the LC-QuAD-1 dataset. We believe, our proposed approach is novel and will lead to dynamic KGQA solutions that are suited for practical applications.

show abstract

“…In this article, we introduced a new method for real-world analysis of open data and demonstrated an example of using ontology. Ontologies are semantically related, so SPARQL queries are imposed to extract useful information [9]. A prototype has been implemented that supports the semantic linking of concepts related to the agricultural, land and rainfall sector datasets published by various departments of the New Zealand government.…”

Section: Introductionmentioning

confidence: 99%

Ontology-Based Semantic Search Framework for Disparate Datasets

Kaur¹,

Nand²,

Naseer³

et al. 2022

Intelligent Automation &Amp; Soft Computing

View full text Add to dashboard Cite

The public sector provides open data to create new opportunities, stimulate innovation, and implement new solutions that benefit academia and society. However, open data is usually available in large quantities and often lacks quality, accuracy, and completeness. It may be difficult to find the right data to analyze a target. There are many rich open data repositories, but they are difficult to understand and use because these data can only be used with a complex set of keyword search options, and even then, irrelevant or insufficient data may eventually be retrieved. To alleviate this situation, ontology-based semantic search has been proven to be an effective way to improve the quality of related content queries in such repositories. In this paper, we propose a new method of semantic linking and storing open government datasets of New Zealand's agriculture, land and rainfall sectors based on the use of ontology. The generated ontology can construct integrated data, in which a unified query can be applied to extract richer and more useful information. To validate our model, we showed how to link ontology manually and automatically. Manual linking requires domain experts, and automatic linking reduces the overhead of relying on domain experts to manually link concepts. The results of this method are promising in terms of improving data quality and search efficiency. In future, the proposed model can be integrated with other domain ontologies.

show abstract

Neural machine translating from natural language to SPARQL

Cited by 47 publications

References 8 publications

Knowledge Graph Question Answering Using Graph-Pattern Isomorphism

Knowledge Graph Question Answering Using Graph-Pattern Isomorphism

Knowledge Graph Question Answering via SPARQL Silhouette Generation

Ontology-Based Semantic Search Framework for Disparate Datasets

Contact Info

Product

Resources

About