Harshit Joshi

josharshit [at] gmail[dot] com

New Delhi, India

I’m am a Software Engineer at Supedio GmbH working on Master Data Management and Medical Entity Resolution. I completed my Bachelors in Information Technology and Mathematics from Cluster Innovation Centre, University of Delhi in July 2021.

I have previously interned with the research team at DRDO, Govt. of India, where I worked on an Image Segmentation task in a simulated Gazebo environment. I spent a summer at Chennai Mathematical Institute as a Mathematical Finance Summer Scholar, working on sliding-window approaches. I have also interned with the Data Science team at Cronycle, UK, building a production-ready RSS aggregating pipeline.

I’m mostly interested in working in Deep Learning, NLP and it’s applications in Computational Social Science. Presently, I am modeling polite requests and tinkering with conversational agents. I have also worked on Suicide Risk Assessment on Social Media, Keyphrase Extraction, and processing invoices.

news (older)

Jul 27, 2021 I am joining Supedio Gmbh as a full-time software engineer working on Master Data Management and medical entity matching
Mar 16, 2021 First Author research paper accepted at AAAI ICWSM 2021! Tweets Classification to Assist Human Moderation for Suicide Prevention.
Mar 11, 2021 First Author long paper accepted at NAACL 2021! Suicide Ideation Detection via Social and Temporal User Representations using Hyperbolic Learning. (Core A)
Jan 29, 2021 Research Paper accepted at JAMIA: Journal of the American Medical Informatics Association. Robust Suicide Risk Assessment on Social Media via Deep Adversarial Learning (IF: 4.112)
Jan 11, 2021 First Author long paper accepted at EACL 2021! PHASE: Learning Emotional Phase-aware Representations for Suicide Ideation Detection on Social Media. (Core A)

selected publications (all)

  1. Tweets Classification to Assist Human Moderation for Suicide Prevention
    Sawhney, Ramit*, Joshi, Harshit*, Nobles, Alicia*, and Shah, Rajiv Ratn
    In Proceedings of the International AAAI Conference on Web and Social Media 2021
  2. Suicide Ideation Detection via Social and Temporal User Representations using Hyperbolic Learning
    Sawhney, Ramit*, Joshi, Harshit*, Shah, Rajiv Ratn, and Flek, Lucie
    In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) 2021
  3. PHASE: Learning Emotional Phase-aware Representations for Suicide Ideation Detection on Social Media
    Sawhney, Ramit*, Joshi, Harshit*, Flek, Lucie, and Shah, Rajiv Ratn
    In Proceedings of 16th Conference of the European Chapter of the Association for Computational Linguistics 2021