feat: Generalized neuro-symbolic prototype (zero-shot, no training)#2
Open
Bentlybro wants to merge 1 commit into
Open
feat: Generalized neuro-symbolic prototype (zero-shot, no training)#2Bentlybro wants to merge 1 commit into
Bentlybro wants to merge 1 commit into
Conversation
New prototype that works on ANY text dataset: - Zero-shot relation discovery using pre-trained transformers (BART-MNLI) - Automatic concept extraction (no entity markup required) - Symbolic KB with forward chaining (reused from original) - Streaming support for large datasets - Domain-agnostic + configurable custom relations Includes Colab notebook with 3 demos: 1. SemEval relation dataset (small, fast) 2. Generative Coding Dataset (29GB, streaming) 3. Customizable 'try your own' cell No training required — just point at a dataset and go.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Dataset-agnostic neuro-symbolic prototype (1347 lines). No training - zero-shot BART-MNLI. Auto concept extraction, any HuggingFace dataset, streaming for large data. Colab with 3 demos: SemEval, Coding Dataset (29GB), and customizable. Alpha - ready for transformer swap.