Mohnish Dubey

Senior Researcher at Smart Data Analytics, and Project Leader at InfAI Dresden, Germany.

About Me

Hi, my name is Mohnish Dubey, and I am a Senior Researcher at Smart Data Analytics and InfAI. Currently, I am leading the e-VITA project at InfAI, working towards designing knowledege graph based dailogue system to support active and healthy ageing.

Previously, I have worked as a Dialogue Engineer at Fraunhofer IAIS for more than three years. In 2021, I compeleted my PhD from University of Bonn, Germany. I have worked in the research area of Question Answering over Knowledge Graphs, Dialogue Systems, Entity Linking, Relation Linking, Large Dataset Generation, Answer Representation, and general NLP and KG tasks.

Projects

AskNowNQS For Question Answering over Knowledge Graph

July 2015 - July 2016

  • Lead to the development of question answering system over DBpedia.
  • Here Natural language questions are normalized into an intermediary canonical syntactic form and then translated into a SPARQL
  • A rule based system for question answering over DBpedia Knowledge Graph
  • source code https://github.com/AskNowQA/AskNowNQS

LC-QuAD- Large scale Complex Question Answering Dataset.

March 2017 - present

  • Lead the project with aim to create a Question Answering data set with the pair of Natural Language question to their corresponding SPARQL query.
  • LC-QuAD 1.0 published a dataset of 5,000 question over DBpedia.
  • LC-QuAD 2.0 published a dataset of 30,000 question over Wikidata.
  • project website: http://lc-quad.sda.tech

EARL - Entity and Relation Linking for KGQA

September 2017 - December 2018

  • Developed the component to performs entity linking and relation linking as a joint single task.
  • First by modeling the problem to Generalised Travelling Salesman Problem.
  • Second using machine learning in order to exploit the connection density between nodes in the knowledge graph.
  • Source code: https://github.com/AskNowQA/EARL

Question Answering over Video Annotation

January 2018 - June 2018

  • In this internal Fraunhofer project we developed a template based question answering system
  • We targeted ARD Video annotations, and fetch videos based on user’s input in German language.

VANiLLa - A dataset for better Answer Representation

January 2020 - December 2020

  • A large scale dataset for answer verbaliser for simple natural questions.
  • The answer in this dataset are syntactically and semantically closer to the question than to the KG triple.
  • Website https://sda.tech/projects/vanilla/

Experience

InfAI Dresden

Project Leader in e-VITA project

May 2021 - Ongoing

https://www.e-vita.coach
  • Developing use-cases and user stories for the dialogue system with the vision of the project of active healthy ageing
  • Investigating several components(such as translation services) and pipelines to use them to meet the project requirements
  • Developing a Dialogue system with RASA framework and further integrating Question Answering capabilities.

Smart Data Analytics, University of Bonn

Senoior Researcher

January 2016 - Present

https://www.sda.tech
  • Defended Ph.D. Thesis on Question Answering over Knowledge Graph (KGQA). (January 2021)
  • Published state of the art systems on KGQA, Entity and Relation Linking and Dataset generation.
  • Managed and supervised student assistants for KGQA project, AskNow.
  • Conducted research on Answer Representation and managed UI development for KGQA.
  • Conducted NLP Labs and Seminars, currently also mentoring master student projects

Fraunhofer IAIS , Sankt Augustin / Dresden

Dialogue Engineer

October 2017 - May 2021

  • Worked on Semantic Question Answering over Knowledge Graph.
  • Lead developer in projects on Question Answering over Video Annotations in German language.
  • Supported with evaluation on Dialogue System for Car Infotainment.
  • Generated Question Answering benchmarking for Conversation AI systems in specific domains such as COVID-19 data, and Financial reports.

AKSW, University of Liepzig

Guest Researcher

June 2015 - December 2015

https://www.aksw.org
  • In the six month internship worked and gained knowledge in the field of Semantic Web and Question Answering.
  • Learned about Knowledge gGraphs and SPARQL Query.
  • Worked on rule based translation of English Questions to SPARQL query.

Research Publication

  • PNEL: Pointer Network based End-To-End Entity Linking over Knowledge Graphs, Debayan Banerjee, Debanjan Chaudhuri, Mohnish Dubey and Jens Lehmann, in Proceedings of International Semantic Web Conference 2020
  • IQA: Interactive query construction in semantic question answering systems, By Hamid Zafar, Mohnish Dubey, Jens Lehmann, Elena Demidova, in Journal of Web Semantics.
  • LC-QuAD 2.0: A large dataset for complex question answering over Wikidata and DBpedia By Mohnish Dubey, Debayan Banerjee, Abdelrahman Abdelkawi, Jens Lehmann in Proceedings of International Semantic Web Conference 2019, New Zealand
  • EARL: Joint Entity and Relation Linking for Question Answering over Knowledge Graphs by Mohnish Dubey, Debayan Banerjee, Debanjan Chaudhuri and Jens Lehmann in Proceedings of International Semantic Web Conference 2018
  • LC-QuAD : A Corpus for Complex Question Answering over Knowledge Graphs by Priyansh Trivedi, Gaurav Maheshwari, Mohnish Dubey and Jens Lehmanni in Proceedings of the International Semantic Web Conference 2017.
  • How to Revert Question Answering on Knowledge Graphs by Gaurav Maheshwari, Mohnish Dubey, Priyansh Trivedi and Jens Lehmann. In Proceedings of the International Semantic Web Conference 2017.
  • AskNow: A Framework for Natural Language Query Formalization in SPARQL by Mohnish Dubey, Sourish Dasgupta, Ankit Sharma, Konrad Hoffner, and Jens Lehmann in Proceedings of the Extended Semantic Web Conference 2016.
  • VANiLLa : Verbalised ANswers in Natural Language at Large scale by Debanjali Biswas, Mohnish Dubey, Md Rashad Al Hasan Rony and Jens Lehmann, under review process.

Education

University of Bonn

Ph.D. in Computer Science

Jan 2016 - Jan 2021

During my PhD at the University of Bonn, I was a part of the Smart Data Analytics group lead by Prof. Jens Lehmann.

DA-IICT, India

Master of Technology

2012 - 2014

At Technology Dhirubhai Ambani Institute of Information & Communication Technology, I completed my master’s degree with machine intelligence speciation. In my master thesis, I worked on the normalization of negative sentences. Here I was first introduced to Semantic Web by Dr Sourish Dasgupta.

JNCT, Bhopal India

Bachelor of Engineering

2008 - 2012

I completed my Engineering degree in Computer Science at Jai Narain College of Technology affiliated to Rajiv Gandhi Proudyogiki Vishwavidyalaya, India. During my last year, I scored 98 percentile in the GATE exam, motivating me to study computer science further.

A Little More About Me

Alongside my interests in research some of my other interests and hobbies are:

  • Huge fan of Cricket.
  • Photo editing and graphics.
  • Picked up intrest in Travelling during my PhD.
  • Listening music.