Shivam Abhilash

Experienced technology leader with a demonstrated history of working in the management consulting industry. Skilled in Machine Learning, NLP, Graph, Production ready ML Solutions, Leadership, Management and Solution Delivery. Strong business development professional graduated from Indian Institute Of Information Technology having knowledge of Data Analytics.

1. A Rule-Based Expert System for Automated Document Editing : This research paper introduces a Rule-Based Expert System designed for the automated editing of documents in PDF and PPT formats.

2. Taking Natural Language Generation and Information Extraction to Domain Specific Tasks : For domains like legal, documents are often needed to be manually analyzed in order to check if all the critical information is present in them and to extract the important points if needed. All these manual domain-specific tasks can be automated with the help of different Natural Language Processing (NLP) and Natural Language Generation (NLG) techniques. In this paper, some of the tools in NLP and NLG that can be used to automate the above-mentioned processes for key information extraction are discussed. 

3.Evidence based Employee Analytics using Taxonomy Enabled Knowledge Graph : In this paper we create a pipeline, by taking dataset comprised of all the sow documents generated by an organization and then generating insights from it. 

4.Jaccard Based Similarity Index in Graphs: A Multi-Hop Approach : In this paper we have proposed a similarity index that is aligned in the lines of Jaccard Coefficient but manages to predict the similarity between two nodes fundamentally on the basis of the shortest path between them. 

5.Link Prediction Using Semi-Automated Ontology and Knowledge Graph in Medical Sphere : This model not only extracts entities which are more specific to the medical domain, but also label them according to the category they belong to. All the entities are classified into subclass and main-class using ontologies. 

6.Graph NLU enabled question answering system : In this paper, we used conversational analytics tool to create the user interface and to get the required entities and intents from the query thus avoiding the traditional semantic parsing approach. 

7.Few shot learning with fine-tuned language model for suicidal text detection : We have proposed an approach to determine early detection with the goal of early diagnosis of suicidal behavior through text posted on social media via supervised learning using few shot learning process. 

8.Video Indexing System Based on Multimodal Information Extraction Using Combination of ASR and OCR : In the current paper, an attempt has been made to index videos based on the visual and audio content of the video. The visual content is extracted using an Optical Character Recognition (OCR) on the stack of frames obtained from a video while the audio content is generated using an Automatic Speech Recognition (ASR).