Template-based Question Answering analysis on the LC-QuAD2.0 Dataset

Dileep, Akshay Kumar; Mishra, Anurag; Mehta, Ria; Uppal, Siddharth; Chakraborty, Jaydeep; Bansal, Srividya K.

doi:10.1109/icsc50631.2021.00079

Cited by 4 publications

(3 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The objective of this study is to compare different classifiers, including random forest classifier [38] and XGBoost classifier, based on different pre-processing techniques, including POS tags, word embeddings and combination of POS tags and word embeddings. Similar to [34], [36],…”

Section: Related Workmentioning

confidence: 93%

“…This model is trained over LC-QuAD dataset [35] which includes 5K questions paired with their SPARQL queries. A comparative study is presented in [36] using the LC-QuAD 2.0 dataset [37] that consists of 30K question-answer pairs. The objective of this study is to compare different classifiers, including random forest classifier [38] and XGBoost classifier, based on different pre-processing techniques, including POS tags, word embeddings and combination of POS tags and word embeddings.…”

Section: Related Workmentioning

confidence: 99%

“…Although template-based approaches can be applied in small and medium scaled KGs, they require much effort to ensure covering every possible question and cannot be easily adapted to new domains. Different from the information retrieval-based and semantic parsing-based methods in [34], [36] which require a considerable amount of training data, we propose an approach to automatically classify questions into their corresponding query patterns for SMEs. First, we deal with the lack of training data in small and medium scaled KGs by generating NLQs over RDF triples in a semiautomated solution.…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Question Answering Over Knowledge Graphs: A Case Study in Tourism

Aghaei

Raad²,

Fensel

2022

IEEE Access

View full text Add to dashboard Cite

Over the recent years, a large number of knowledge graphs (KGs) have been developed to store and present small and medium enterprises' data in the form of subject-predicate-object triples. The KGs are not easily accessible to end-users because they need an understanding of query languages and KGs' structures. To assist end-users in accessing these KGs, question answering over KGs targets to provide answers for natural language questions (NLQs). This paper proposes an approach to answer questions over small and medium scaled KGs based on graph isomorphism in two phases: (1) offline phase and (2) semantic parsing phase. In the offline phase, a semi-automated solution is proposed to generate NLQs and their answers, which are used to train machine learning models employed in the next phase. In the semantic parsing phase, a given input NLQ is mapped into a query pattern according to its grammatical structure. Each query pattern contains some slots that need to be filled with corresponding entities, classes and relations from the KG. While string and semantic similarity metrics are applied to identify the entities and classes, the probability distribution of the relations is used to extract the relations. The Cartesian product of the identified entities, classes and relations is utilized to fill the slots, derive SPARQL queries and finally retrieve the answers. To evaluate the proposed approach, we use SalzburgerLand KG, a real KG describing touristic entities of the region of Salzburg, Austria. Our results show that the approach improves the end-to-end user experience in terms of interactive question answering and performance.

show abstract

Section: Related Workmentioning

confidence: 93%