Details
| Original language | English |
|---|---|
| Media of output | Online |
| Publication status | Published - 8 Mar 2023 |
Abstract
The dump can be imported into a virtuoso endpoint or any RDF engine so it can be queried. The questions/queries are provided as spread sheets (Excel format & CSV format), also train and test files are provided. Types of questions and queries: Handcrafted set of 100 questions Auto-generated set of 2465 questions More details on certain columns:
"Classification rationale" It may contain the following values: Nested facts in the question Sorting, sum, average, minimum, maximum or count calculation required Filter used Mappings of Asking Point in the question to the ORKG ontology Explanation of Rationale for Non-factoid: Nested facts in the question. An entity (e.g., a system or a paper) or predicate is requested that is not explicitly stated in the question text and must be inferred while searching for an answer. Sorting, sum, average, minimum, maximum or count calculation required. To get the answer to the question it is necessary to make an aggregation of the query results. Filter used. To get the answer to the question it is necessary to use filtering of the query results by some conditions.
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
Research output: Non-textual form › Software › Research › peer review
}
TY - ADVS
T1 - SciQA benchmark
T2 - Dataset and RDF dump
AU - Auer, Sören
AU - Barone, Dante
AU - Bartz, Cassiano
AU - Cortes, Eduardo Gabriel
AU - Jaradeh, Mohamad Yaser
AU - Karras, Oliver
AU - Koubarakis, Manolis
AU - Mouromtsev, Dmitry
AU - Pliukhin, Dmitrii
AU - Radyush, Daniil
AU - Shilin, Ivan
AU - Stocker, Markus
AU - Tsalapati, Eleni
PY - 2023/3/8
Y1 - 2023/3/8
N2 - SciQA benchmark of questions and queries. The data dump is in NTriples format (RDF NT) taken from the orkg system on 14.03.2023 at 02:04PM.The dump can be imported into a virtuoso endpoint or any RDF engine so it can be queried. The questions/queries are provided as spread sheets (Excel format & CSV format), also train and test files are provided. Types of questions and queries: Handcrafted set of 100 questions Auto-generated set of 2465 questions More details on certain columns:"Classification rationale" It may contain the following values: Nested facts in the question Sorting, sum, average, minimum, maximum or count calculation required Filter used Mappings of Asking Point in the question to the ORKG ontology Explanation of Rationale for Non-factoid: Nested facts in the question. An entity (e.g., a system or a paper) or predicate is requested that is not explicitly stated in the question text and must be inferred while searching for an answer. Sorting, sum, average, minimum, maximum or count calculation required. To get the answer to the question it is necessary to make an aggregation of the query results. Filter used. To get the answer to the question it is necessary to use filtering of the query results by some conditions.
AB - SciQA benchmark of questions and queries. The data dump is in NTriples format (RDF NT) taken from the orkg system on 14.03.2023 at 02:04PM.The dump can be imported into a virtuoso endpoint or any RDF engine so it can be queried. The questions/queries are provided as spread sheets (Excel format & CSV format), also train and test files are provided. Types of questions and queries: Handcrafted set of 100 questions Auto-generated set of 2465 questions More details on certain columns:"Classification rationale" It may contain the following values: Nested facts in the question Sorting, sum, average, minimum, maximum or count calculation required Filter used Mappings of Asking Point in the question to the ORKG ontology Explanation of Rationale for Non-factoid: Nested facts in the question. An entity (e.g., a system or a paper) or predicate is requested that is not explicitly stated in the question text and must be inferred while searching for an answer. Sorting, sum, average, minimum, maximum or count calculation required. To get the answer to the question it is necessary to make an aggregation of the query results. Filter used. To get the answer to the question it is necessary to use filtering of the query results by some conditions.
U2 - 10.5281/zenodo.5845197
DO - 10.5281/zenodo.5845197
M3 - Software
ER -