Debayan Banerjee

I am a Doctoral Student at the Language Technology Group of the University of Hamburg, Germany. I am co-supervised by Prof. Dr. Chris Biemann and Prof. Dr. Ricardo Usbeck. My area of interest lies broadly in the field of Natural Language Processing, and currently, I focus on Question Answering over Knowledge Graphs.

I completed my Bachelors in Information Technology in 2009 at the National Institute of Technology, Durgapur, India. I spent the next 7 years in the software industry, of which 4 years I spent as a co-founder of Gazemetrix Inc. After Gazemetrix, I worked at paytm.com in the DevOps team.

In 2017 I took a break from the industry and resumed my academic journey. I started my M.Sc. in Computer Science at the University of Bonn, Germany where I worked under Prof. Dr. Jens Lehmann on Knowledge Graph Question Answering.

Google Scholar  /  Twitter  /  Github

profile photo
News

01.02.2024 Starting today, I joined the Leuphana University at Lüneburg, as an Akademischer Rat (Academic Advisor) in the Artificial Intelligence and Explainability Group of Ricardo Usbeck.

14.12.2023 Proceedings for the Scholarly QALD challenge 2023 are now online at https://ceur-ws.org/Vol-3592/

26.09.2023 I am co-organising the first Scholarly Question Answering challenge at ISWC 2023. Please check link for further details.

04.09.2023 Demo paper accepted at ISWC 2023. Link can be found in paper section below.

08.08.2023 Reviewed for the EMNLP 2023 industry track.

28.05.2023 Presented my research paper at ESWC 2023 in Heraklion, Greece. Link to video.

Research Papers
DBLPLink: An Entity Linker for the DBLP Scholarly Knowledge Graph
Debayan Banerjee, Arefa, Ricardo Usbeck, Chris Biemann
ISWC 2023 Demo Paper

A web application that performs entity linking over the DBLP KG.

The Role of Output Vocabulary in T2T LMs for SPARQL Semantic Parsing
Debayan Banerjee, Pranav Ajit Nair, Ricardo Usbeck, Chris Biemann
ACL Findings 2023 Short Paper
* Pranav and I are equal authors

We show that certain vocabularies are better than others for the task of semantic parsing.

GETT-QA: Graph Embedding based T2T Transformer for Knowledge Graph Question Answering
Debayan Banerjee, Pranav Ajit Nair, Ricardo Usbeck, Chris Biemann
ESWC 2023 Research Track
arXiv

We show that T5 can generate logical forms and also learn a simple embedding space for entities.

DBLP-QuAD: A Question Answering Dataset over the DBLP Scholarly Knowledge Graph
Debayan Banerjee, Sushil Awale, Ricardo Usbeck, Chris Biemann
The 13th International Workshop on Bibliometric-enhanced Information Retrieval @ ECIR 2023
arXiv

A dataset consisting of 10,000 question/answer pairs and corresponding SPARQL query over the DBLP scholarly knowledge graph.

A System for Human-AI collaboration for Online Customer Support
Debayan Banerjee*, Mathis Poser*, Christina Wiethof*, Varun Shankar, Richard Paucar, Eva Bittner, Chris Biemann,
The AAAI 2023 Workshop on Representation Learning for Responsible Human-Centric AI
arXiv

We present a system that enables human-AI collaboration for online customer support.

ARDIAS: AI-Enhanced Research Management, Discovery, and Advisory System
Debayan Banerjee, Seid Muhie Yimam, Sushil Awale, Chris Biemann,
The AAAI 2023 Workshop on Scientific Document Understanding
arXiv / Demo

We present a web interface for exploring the web of scholarly data.

Modern Baselines for SPARQL Semantic Parsing
Debayan Banerjee, Pranav Ajit Nair*, Jivat Neet Kaur*, Ricardo Usbeck, Chris Biemann,
SIGIR, 2022
arXiv / Code

We evaluate the performance of contemporary Text-2-Text pre-trained language models against a Pointer Generator Network in the task of SPARQL Semantic Parsing.

Let’s Team Up with AI! Toward a Hybrid Intelligence System for Online Customer Service
Mathis Poser, Christina Wiethof, Debayan Banerjee, Varun Shankar, Richard Paucar, Eva Bittner
DESRIST, 2022. Best Student Paper Award.
Paper

Hybrid Intelligence Systems help overcome current pitfalls in Customer Support Services by combining the complementary strengths of artificial and human intelligence.

PNEL: Pointer Network Based End-To-End Entity Linking over Knowledge Graphs
Debayan Banerjee, Debanjan Chaudhuri, Mohnish Dubey, Jens Lehmann
ISWC, 2020.
arXiv / Code

A Pointer Network is employed in the task of Entity Linking.

LC-QuAD 2.0: A Large Dataset for Complex Question Answering over Wikidata and DBpedia
Mohnish Dubey, Debayan Banerjee, Abdelrehman Abdelkawi Jens Lehmann
ISWC, 2019.
Paper / Dataset

A large question answering dataset over Wikidata and DBpedia Knowledge Graphs is developed and shared with the community.

EARL: Joint Entity and Relation Linking for Question Answering over Knowledge Graphs
Mohnish Dubey, Debayan Banerjee, Debanjan Chaudhuri Jens Lehmann
ISWC, 2018.
Paper / Code

Joint Entity and Relation Linking problem is framed as a Travelling Salesman Problem and solved approximately.

Harvesting information from captions for weakly supervised semantic segmentation
Johann Sawatzky, Debayan Banerjee, Juergen Gall
ICCV, 2019 Workshop Paper.
Paper

Images are segmented based on their text captions.


Website Template taken from John Barron.