List of projects that I am currently working on.

Document level Relation Extraction from Text

📢 Document-level relation extraction is a challenging task that involves identifying relationships between entities within a document. Link prediction techniques, which aim to predict the likelihood of links between nodes in a graph, have been successfully applied to relation extraction tasks. In this work, we propose a context-aware link prediction approach for improving document-level relation extraction.

Relation Extraction from Biomedical Text

📢 Relation Extraction (RE) is the task of extracting semantic relationships between entities in a sentence and aligning them to relations defined in a vocabulary, which is generally in the form of a Knowledge Graph (KG) or an ontology. Various approaches have been proposed so far to address this task. However, applying these techniques to biomedical text often yields unsatisfactory results because it is hard to infer relations directly from sentences due to the nature of the biomedical relations. To address these issues, we present a novel technique called ReOnto, that makes use of neuro-symbolic knowledge for the RE task. ReOnto employs a graph neural network to acquire the sentence representation and leverages publicly accessible ontologies as prior knowledge to identify the sentential relation between two entities.

An Ontology and Rule based System to Assist Doctors in NICUs

📢 Babies born before 34 to 37 weeks (admitted to NICU) often have problems feeding from a bottle or a breast. They are watched closely to make sure they are getting the right balance of fluids and nutrition. We are developing an ontology based nutrition guideline system which captures all the current information of neonates like day of life, sign and symptom and others in integration with rules built with the help of medical experts and guidelines available. This system will assist the clinicians, and provide the relevant feed amounts to give to a neonate based on its present condition .

Ontology Enrichment Benchmark

📢 Ontology learning is the process of building ontologies automatically from unstructured data sources such as text. Several ontology learning systems have been developed, but they have been trained and tested on different datasets. In order to evaluate and compare these systems as well as make progress in ontology learning, it is critical to have good benchmarks. In this project, we work on generating text with annotations that can be used to build ontologies with different types of axioms.

Ontology Enrichment using Union and Intersection Axioms

📢Many ontologies, especially the ones created automatically by the ontology learning systems, have only shallow relationships between the concepts, i.e., simple subclass relations. Expressive axioms such as the class union and intersection are not part of the ontology. These axioms make the ontology rich and play an essential role in the performance of downstream applications. However, such relations are generally part of the text documents. We are working on extracting union and intersection axioms from text using entity linking and taxonomic tree search.