A5002627051- Topic Modeling
- Natural Language Processing Techniques
- Advanced Graph Neural Networks
- Semantic Web and Ontologies
- Biomedical Text Mining and Ontologies
- Data Quality and Management
- Service-Oriented Architecture and Web Services
- Advanced Database Systems and Queries
- Cloud Computing and Resource Management
- Multimodal Machine Learning Applications
- Advanced Malware Detection Techniques
- Explainable Artificial Intelligence (XAI)
- Recommender Systems and Techniques
- Advanced Text Analysis Techniques
- Speech and dialogue systems
- Geographic Information Systems Studies
- Adversarial Robustness in Machine Learning
- High-Temperature Coating Behaviors
- Teaching and Learning Programming
- Indigenous Knowledge Systems and Agriculture
- Data Management and Algorithms
- Optimization and Variational Analysis
- Metal and Thin Film Mechanics
- Agricultural Innovations and Practices
- GABA and Rice Research
Barkatullah University
2023-2024
Zero Emissions Resource Organisation
2021
Fraunhofer Institute for Intelligent Analysis and Information Systems
2016-2021
University of Bonn
2017-2021
Agricultural & Applied Economics Association
2021
Chaudhary Charan Singh Haryana Agricultural University
2021
Guru Jambheshwar University of Science and Technology
2021
J.C. Bose University of Science & Technology, YMCA
2021
Fraunhofer Society
2018
Fraunhofer Institute for Algorithms and Scientific Computing
2018
Modern question answering (QA) systems need to flexibly integrate a number of components specialised fulfil specific tasks in QA pipeline. Key include Named Entity Recognition and Disambiguation, Relation Extraction, Query Building. Since different software exist that implement strategies for each these tasks, it is major challenge select combine the most suitable into system, given characteristics question. We study this optimisation problem train classifiers, which take features as input...
Ahmad Sakor, Isaiah Onando Mulang', Kuldeep Singh, Saeedeh Shekarpour, Maria Esther Vidal, Jens Lehmann, Sören Auer. Proceedings of the 2019 Conference North American Chapter Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). 2019.
In this paper, we present a novel method named RECON, that automatically identifies relations in sentence (sentential relation extraction) and aligns to knowledge graph (KG). RECON uses neural network learn representations of both the as well facts stored KG, improving overall extraction quality. These facts, including entity attributes (label, alias, description, instance-of) factual triples, have not been collectively used state art methods. We evaluate effect various forms representing KG...
Endri Kacupaj, Joan Plepi, Kuldeep Singh, Harsh Thakkar, Jens Lehmann, Maria Maleshkova. Proceedings of the 16th Conference European Chapter Association for Computational Linguistics: Main Volume. 2021.
Pretrained Transformer models have emerged as state-of-the-art approaches that learn contextual information from the text to improve performance of several NLP tasks. These models, albeit powerful, still require specialized knowledge in specific scenarios. In this paper, we argue context derived a graph (in our case: Wikidata) provides enough signals inform pretrained transformer and their for named entity disambiguation (NED) on Wikidata KG. We further hypothesize proposed KG can be...
Abstract In the last decade, a large number of knowledge graph (KG) completion approaches were proposed. Albeit effective, these efforts are disjoint, and their collective strengths weaknesses in effective KG have not been studied literature. We extend Plumber , framework that brings together research community’s disjoint on completion. include more components into architecture to comprise 40 reusable for various subtasks, such as coreference resolution, entity linking, relation extraction....
Large amounts of geospatial data have been made available recently on the linked open cloud and portals many national cartographic agencies (e.g., OpenStreetMap data, administrative geographies various countries, or land cover/land use sets). These datasets vocabularies can be queried using SPARQL its OGC-standardized extension GeoSPARQL. In this paper we go beyond these approaches to offer a question answering service top sources. Our system has implemented as re-usable components Qanary...
Research has seen considerable achievements concerning translation of natural language patterns into formal queries for Question Answering (QA) based on Knowledge Graphs (KG). One the main challenges in this research area is about how to identify which property within a Graph matches predicate found Natural Language (NL) relation. Current approaches query generation attempt resolve problem mainly by first retrieving named entity from KG together with list its predicates, then filtering out...
Abhishek Nadgeri, Anson Bastos, Kuldeep Singh, Isaiah Onando Mulang', Johannes Hoffart, Saeedeh Shekarpour, Vijay Saraswat. Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021.
Restaurant recommendation system is a very popular service whose accuracy and sophistication keeps increasing every day. With the advent of smartphones, web 2.0 internet services like 3G, this has become accessible by consumer. In paper, we present personalized location based restaurant integrated in mobile technology. It ubiquitously studies user's behavioral pattern visiting using Machine Learning algorithm. We also address issues faced today's systems propose methods to rectify it.
Manoj Prabhakar Kannan Ravi, Kuldeep Singh, Isaiah Onando Mulang’, Saeedeh Shekarpour, Johannes Hoffart, Jens Lehmann. Proceedings of the 16th Conference European Chapter Association for Computational Linguistics: Main Volume. 2021.
This paper addresses the task of conversational question answering (ConvQA) over knowledge graphs (KGs). The majority existing ConvQA methods rely on full supervision signals with a strict assumption availability gold logical forms queries to extract answers from KG. However, creating such form is not viable for each potential in real-world scenario. Hence, case missing forms, information retrieval-based approaches use weak via heuristics or reinforcement learning, formulating as KG path...
Transforming natural language questions into formal queries is an integral task in Question Answering (QA) systems. QA systems built on knowledge graphs like DBpedia, require a step after processing for linking words, specifically including named entities and relations, to their corresponding graph. To achieve this task, several approaches rely background bases containing semantically-typed e.g., PATTY, extra disambiguation step. Two major factors may affect the performance of relation...
Question answering (QA) is one of the biggest challenges for making sense out data. The Web Data has attracted attention QA community and recently, a number schema-aware systems have been introduced. While research achievements are individually significant, yet, integrating different approaches not possible due to lack systematic approach conceptually describing systems. In this paper, we present message-driven vocabulary built upon an abstract level. This concluded from conceptual views...
The Natural Language Processing (NLP) community has significantly contributed to the solutions for entity and relation recognition from a natural language text, possibly linking them proper matches in Knowledge Graphs (KGs). Considering Wikidata as background KG, there are still limited tools link knowledge within text Wikidata. In this paper, we present Falcon 2.0, first joint tool over It receives short English outputs ranked list of entities relations annotated with candidates represented...