CONQUEST: A Framework for Building Template-Based IQA Chatbots for Enterprise Knowledge Graphs

Avila, Caio Viktor S.; Franco, Wellington; Maia, José Gilvan Rodrigues; Vidal, Vânia Maria Ponte

doi:10.1007/978-3-030-51310-8_6

Cited by 5 publications

(5 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…How can response generation be implemented? All of the above types utilize some type of knowledge graph to formalize the configuration [70,6] and the intended output format of the conversation [50,3] [22], as well as BPMN based solutions to encode potential progressions of a conversation [55] have been proposed. One example of such a system is PACA [38].…”

Section: How Do Chatbots Work and What Are Important Areas Of Applica...mentioning

confidence: 99%

Conversational Process Modelling: State of the Art, Applications, and Implications in Practice

Klievtsova,

Benzin,

Kampik

et al. 2023

Lecture Notes in Business Information Processing

View full text Add to dashboard Cite

Chatbots such as ChatGPT have caused a tremendous hype lately. For BPM applications, it is often not clear how to apply chatbots to generate business value. Hence, this work aims at the systematic analysis of existing chatbots for their support of conversational process modelling as process-oriented capability. Application scenarios are identified along the process life cycle. Then a systematic literature review on conversational process modelling is performed. The resulting taxonomy serves as input for the identification of application scenarios for conversational process modelling, including paraphrasing and improvement of process descriptions. The application scenarios are evaluated for existing chatbots based on a real-world test set from the higher education domain. It contains process descriptions as well as corresponding process models, together with an assessment of the model quality. Based on the literature and application scenario analyses, recommendations for the usage (practical implications) and further development (research directions) of conversational process modelling are derived.

show abstract

Section: How Do Chatbots Work and What Are Important Areas Of Applica...mentioning

confidence: 99%

Conversational Process Modelling: State of the Art, Applications, and Implications in Practice

Klievtsova,

Benzin,

Kampik

et al. 2023

Lecture Notes in Business Information Processing

View full text Add to dashboard Cite

show abstract

“…The closest work to ours is by Athreya et al [3] based on a tree-based RNN to learn different templates on LC-QuAD v1 which the authors directly derive from the LC-QuAD v1 inherent SPARQL templates and thus cannot generalize to other KGs or datasets. CONQUEST [4] is an enterprise KGQA system which also assumes the SPARQL templates are given. It then matches the questions and templates by vectorizing both and training one classifier, namely Gaussian Naïve Bayes.…”

Section: Related Workmentioning

confidence: 99%

“…2 Consider the question Who was the doctoral mentor of Einstein?. DBpedia contains only the relation dbo:doctoralAdvisor 3 and not dbp:mentor 4 . Through the synonym advisor of mentor, the relation dbo:doctoralAdvisor can be determined.…”

Section: Relation Index and Class Indexmentioning

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

“…The closest work to ours is by Athreya et al [3] based on a tree-based RNN to learn different templates on LC-QuAD v1 which the authors directly derive from the LC-QuAD v1 inherent SPARQL templates and thus cannot generalize to other KGs or datasets. CON-QUEST [4] is an enterprise KGQA system which also assumes the SPARQL templates are given. It then matches the questions and templates by vectorizing both and training one classifier, namely Gaussian Naïve Bayes.…”

Section: Related Workmentioning

confidence: 99%

“…The indexes are used to map n-grams to relations and classes of the ontologies of the KB.TeBaQA additionally indexes hypernyms and synonyms for all relations and classes. 4 Consider the question Who was the doctoral mentor of Einstein?. DBpedia contains only the relation dbo:doctoralAdvisor 5 and not dbp:mentor 6 .…”

Section: Information Extractionmentioning

confidence: 99%

Knowledge Graph Question Answering using Graph-Pattern Isomorphism

Vollmers,

Jalota,

Moussallem

et al. 2021

Preprint

View full text Add to dashboard Cite

Knowledge Graph Question Answering (KGQA) systems are 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 finegrained evaluation on complex queries that deal with aggregation and superlative questions as well as an ablation study, highlighting future research challenges.

show abstract

CONQUEST: A Framework for Building Template-Based IQA Chatbots for Enterprise Knowledge Graphs

Cited by 5 publications

References 11 publications

Conversational Process Modelling: State of the Art, Applications, and Implications in Practice

Conversational Process Modelling: State of the Art, Applications, and Implications in Practice

Knowledge Graph Question Answering Using Graph-Pattern Isomorphism

Knowledge Graph Question Answering using Graph-Pattern Isomorphism

Contact Info

Product

Resources

About