2020, Jaradeh, Mohamad Yaser, Stocker, Markus, Auer, Sören, Hall, Mark, Merčun, Tanja, Risse, Thomas, Duchateau, Fabien

Answering questions on scholarly knowledge comprising text and other artifacts is a vital part of any research life cycle. Querying scholarly knowledge and retrieving suitable answers is currently hardly possible due to the following primary reason: machine inactionable, ambiguous and unstructured content in publications. We present JarvisQA, a BERT based system to answer questions on tabular views of scholarly knowledge graphs. Such tables can be found in a variety of shapes in the scholarly literature (e.g., surveys, comparisons or results). Our system can retrieve direct answers to a variety of different questions asked on tabular data in articles. Furthermore, we present a preliminary dataset of related tables and a corresponding set of natural language questions. This dataset is used as a benchmark for our system and can be reused by others. Additionally, JarvisQA is evaluated on two datasets against other baselines and shows an improvement of two to three folds in performance compared to related methods.

2020, Say, Zeynep, Fathalla, Said, Vahdati, Sahar, Lehmann, Jens, Auer, Sören, Hall, Mark, Merčun, Tanja, Risse, Thomas, Duchateau, Fabien

The network of scholarly publishing involves generating and exchanging ideas, certifying research, publishing in order to disseminate findings, and preserving outputs. Despite enormous efforts in providing support for each of those steps in scholarly communication, identifying knowledge fragments is still a big challenge. This is due to the heterogeneous nature of the scholarly data and the current paradigm of distribution by publishing (mostly document-based) over journal articles, numerous repositories, and libraries. Therefore, transforming this paradigm to knowledge-based representation is expected to reform the knowledge sharing in the scholarly world. Although many movements have been initiated in recent years, non-technical scientific communities suffer from transforming document-based publishing to knowledge-based publishing. In this paper, we present a model (PharmSci) for scholarly publishing in the pharmaceutical research domain with the goal of facilitating knowledge discovery through effective ontology-based data integration. PharmSci provides machine-interpretable information to the knowledge discovery process. The principles and guidelines of the ontological engineering have been followed. Reasoning-based techniques are also presented in the design of the ontology to improve the quality of targeted tasks for data integration. The developed ontology is evaluated with a validation process and also a quality verification method.

2018, Singh, K., Radhakrishna, A.S., Both, A., Shekarpour, S., Lytra, I., Usbeck, R., Vyas, A., Khikmatullaev, A., Punjani, D., Lange, C., Vidal, Maria-Esther, Lehmann, J., Auer, Sören

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 the effectiveness of the pipelines generated by Frankenstein using the QALD and LC-QuAD benchmarks. These results not only suggest that Frankenstein precisely solves the QA optimisation problem but also enables the automatic composition of optimised QA pipelines, which outperform the static Baseline QA pipeline. Thanks to this flexible and fully automated pipeline generation process, new QA components can be easily included in Frankenstein, thus improving the performance of the generated pipelines.