Sushil Awale

I am a Research Associate in the Visual Analytics Research Group at TIB, Hannover and a PhD candidate at Leibniz Universität Hannover. I’m supervised by Prof. Dr. Ralph Ewerth. My research interests are in Multimodal Information Retrieval, Question Answering and Knowledge Graphs.

Previously, I worked as a Student Assistant in the Language Technology Group, Universität Hamburg building an intelligent scholarly system powered by Natural Language Processing (NLP).

I completed my Masters in Machine Learning from Universität Hamburg, Germany in 2023 and my Bachelors in Computer Science in 2020 from Tribhuwan University, Nepal.

news

Apr 15, 2023	Started working as Research Associate in the Visual Analytics Research Group at TIB, Hannover, Germany
Mar 13, 2023	Our paper DBLP-QuAD: A Question Answering Dataset over the DBLP Scholarly Knowledge Graph (Banerjee et. al., BIR 2023) accepted in BIR Workshop at ECIR 2023
Dec 15, 2022	Our paper ARDIAS: AI-Enhanced Research Management, Discovery, and Advisory System (Banerjee et. al., SDU@AAAI 2023) accepted in SDU Workshop at AAAI 2023

selected publications

BIR 2023

DBLP-QuAD: A Question Answering Dataset over the DBLP Scholarly Knowledge Graph

Debayan Banerjee, Sushil Awale, Ricardo Usbeck, and 1 more author

13th International Workshop on Bibliometric-enhanced Information Retrieval co-located with the European Conference on Information Retrieval, BIR@ECIR 2023, Dublin, Ireland, April 1 2023

Abs PDF Code

In this work we create a question answering dataset over the DBLP scholarly knowledge graph (KG). DBLP is an on-line reference for bibliographic information on major computer science publications that indexes over 4.4 million publications published by more than 2.2 million authors. Our dataset consists of 10,000 question answer pairs with the corresponding SPARQL queries which can be executed over the DBLP KG to fetch the correct answer. DBLP-QuAD is the largest scholarly question answering dataset.
EURASIA 2022

Enriching Hindi WordNet Using Knowledge Graph Completion Approach

Sushil Awale, and Abhik Jana

In Workshop on Resources and Technologies for Indigenous, Endangered and Lesser-resourced Languages in Eurasia co-located with the Language Resources and Evaluation Conference, EURASIA@LREC 2022 Marseille, France, June 20 Jun 2022

Abs PDF Code

Even though the use of WordNet in the Natural Language Processing domain is unquestionable, creating and maintaining WordNet is a cumbersome job and it is even difficult for low resource languages like Hindi. In this study, we aim to enrich the Hindi WordNet automatically by using state-of-the-art knowledge graph completion (KGC) approaches. We pose the automatic Hindi WordNet enrichment problem as a knowledge graph completion task and therefore we modify the WordNet structure to make it appropriate for applying KGC approaches. Second, we attempt five KGC approaches of three different genres and compare the performances for the task. Our study shows that ConvE is the best KGC methodology for this specific task compared to other KGC approaches.