conditional-text-generation
Contextualized Literature-based Discovery
3260 papers • 126 benchmarks • 313 datasets
Given a seed term (e.g., a task or method in NLP, or a disease in biomedicine) and corresponding background (e.g., challenges for a given task), the model's aim is to generate idea suggestions. The Contextual Literature-Based Discovery (CLBD) will take two different formulations of C-LBD: idea sentence generation and idea node prediction.
(Image credit: Papersgraph)
Benchmarks
These leaderboards are used to track progress in conditional-text-generation
Trend
Dataset
Best Model
Actions
No benchmarks available.
Libraries
iUse these libraries to find conditional-text-generation models and implementations
Datasets
No datasets available.
Subtasks
No subtasks available.
Most implemented papers
SciMON: Scientific Inspiration Machines Optimized for Novelty
Qingyun Wang, Doug Downey, Tom Hope, Heng Ji•Mon May 22 2023
SciMON is presented, a modeling framework that uses retrieval of "inspirations" from past scientific papers, and explicitly optimizes for novelty by iteratively comparing to prior papers and updating idea suggestions until sufficient novelty is achieved.
138