DomiKnowS
A Declarative Learning Based Programming Framework For Integration of Domain Knowledge in Statistical Learning.
We seek for abstractions that facilitate writing programs that can learn from data. We are interested in languages that can help in integration of learning and reasoning formalisms and the formulation of declarative and procedural domain knowledge for learners.
Team Members
- Parisa Kordjamshidi, James Allen, Choh Man Teng, Andrzej Uszok, Brent Kristen Venable, Alex Wan, Tanawan Premsri.
- Hossein Faghihi, Darius Nafar, Chen Zheng, Yue Zhang, Roshanak Mirzaee.
Source of funding
- Office of Naval Research (ONR).
List of publications:
- Prompt2DeModel: Declarative Neuro-Symbolic Modeling with Natural Language. Hossein Rajaby Faghihi, Aliakbar Nafar, Andrzej Uszok, Hamid Karimian, Parisa Kordjamshidi More detail. GitHub. Download.
- GLUECons, A Generic Benchmark for Learning Under Constraints. Hossein Rajaby Faghihi, Aliakbar Nafar, Chen Zheng, Roshanak Mirzaee, Yue Zhang, Andrzej Uszok, Alexander Wan, Tanawan Premsri, Dan Roth, and Parisa Kordjamshidi More detail. GitHub. Download.
- DomiKnowS: A Library for Integration of Symbolic Domain Knowledge in Deep Learning. Hossein Rajaby Faghihi, Quan Guo, Andrzej Uszok, Aliakbar Nafar, Elaheh Raisi, Parisa Kordjamshidi More detail. GitHub. Download.
- Inference-Masked Loss for Structured Output Learning. Quan Guo, Hossein Rajaby Faghihi, Yue Zhang, Andrzej Uszok and Parisa Kordjamshidi More detail. GitHub. Download.
- Latent Alignment of Procedural Concepts in Multimodal Recipes. Hossein Rajaby Faghihi, Roshanak Mirzaee, Sudarshan Paliwal and Parisa Kordjamshidi
