Torsten Scholak
Research Scientist
Human Machine Interaction Through Language
Torsten is an Applied Research Scientist and project leader in the Human-Machine Interaction Through Language program at ServiceNow Research. His current research interest is deep learning for code, especially with large language models and integrating symbolic reasoning. In 2022, he is co-organizing the Deep Learning for Code workshop at ICLR. Previously, he has been more focused on semantic parsing. He has published several papers on translating natural language questions into SQL queries. One of his most successful works on this topic is the PICARD project, which is a state-of-the-art text-to-SQL parser.
Interests
- Large Language Models
- Text2Code
Publications
UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models.
Conference on Empirical Methods in Natural Language Processing (EMNLP),
2022.
Towards Neural Functional Program Evaluation.
Conference on Neural Information Processing Systems (NeurIPS),
2021.
Picard: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Models.
Conference on Empirical Methods in Natural Language Processing (EMNLP),
2021.
DuoRAT: Towards Simpler Text-to-SQL Models.
North American Chapter of the Association for Computational Linguistics (NAACL),
2021.