In Loving Memory of Dragomir Radev

The Salesforce AI Team is mourning the loss of our beloved friend and mentor, Dragomir Radev.

Our team was first introduced to Drago in November 2018 when he gave a talk at our Research Speaker Series. His passion for research beamed through his talk and our leadership team unanimously decided to offer Drago a more permanent collaboration. Drago joined us as a Visiting Professor and was a valued member of our team. When we asked him why he was interested in joining Salesforce, he told us he was looking forward to writing more papers, mentoring young researchers, helping us build out our research team, and working on exciting new research projects. Drago accomplished that and so much more.

Even after his tenure at Salesforce, he continued to collaborate with us and mentor many of our current and past employees. He was very dedicated to all the projects that he was a part of and was always excited to showcase his newest findings.

Drago was not only an exceptional computer scientist, but one of the kindest and most humble people many of us have ever known. He talked so highly of his family and loved sharing stories with many of us through the years. We are so grateful for all the time we have had with Drago.

If you would like to share memories of Drago, Yale has created a memorial website. In addition, a GoFundMe page has been created to help provide support for Drago’s family.

Thank you for everything Drago, you will be missed ❤️

Academic Papers Published with Professor Radev Between 2019-2023:

• SParC: Cross-Domain Semantic Parsing in Context
• Editing-Based SQL Query Generation for Cross-Domain Context-Dependent Questions
• CoSQL: A Conversational Text-to-SQL Challenge Towards Cross-Domain Natural Language Interfaces to Databases
• ESPRIT: Explaining Solutions to Physical Reasoning Tasks
• CO-Search: COVID-19 Information Retrieval with Semantic Search, Question Answering, and Abstractive Summarization
• DART: Open-Domain Structured Data Record to Text Generation
• SummEval: Re-evaluating Summarization Evaluation
• GraPPa: Grammar-Augmented Pre-Training for Table Semantic Parsing
• Universal Natural Language Processing with Limited Annotations: Try Few-shot Textual Entailment as a Start
• FeTaQA: Free-form Table Question Answering
• BookSum: A Collection of Datasets for Long-form Narrative Summarization
• DocNLI: A Large-scale Dataset for Document-level Natural Language Inference
• Uni-Parser: Unified Semantic Parser for Question Answering on Knowledge Base and Table
• Revisiting the Gold Standard: Grounding Summarization Evaluation with Robust Human Evaluation
• Towards Interpretable and Efficient Automatic Reference-Based Summarization Evaluation
• FOLIO: Natural Language Reasoning with First-Order Logic
• Modeling Textual Question Answer as Semantic Parsing with Execution