yoichi1484 / subspace
An implementation of "Subspace Representations for Soft Set Operations and Sentence Similarities" (NAACL 2024)
☆10Updated 5 months ago
Related projects ⓘ
Alternatives and complementary repositories for subspace
- Checkpointable dataset utilities for foundation model training☆32Updated 9 months ago
- ☆10Updated 2 years ago
- ☆11Updated 3 years ago
- ☆32Updated 2 years ago
- Variable-order CRFs with structure learning☆16Updated 3 months ago
- HPYLMのC++実装☆11Updated 7 years ago
- ☆46Updated 2 years ago
- Capturing Set-Theoretic Semantics of Words using Box Embeddings☆34Updated 2 years ago
- ☆12Updated 5 months ago
- ☆10Updated 4 years ago
- ☆16Updated last year
- Minimum Description Length probing for neural network representations☆16Updated last week
- Discovering Universal Geometry in Embeddings with ICA☆16Updated last month
- ☆12Updated last year
- ☆28Updated 2 years ago
- 🌾 Universal, customizable and deployable fine-grained evaluation for text generation.☆22Updated last year
- An attempt to merge ESBN with Transformers, to endow Transformers with the ability to emergently bind symbols☆14Updated 3 years ago
- toy ccg parser☆14Updated 8 years ago
- ☆43Updated 3 years ago
- [ACL 2023]: Training Trajectories of Language Models Across Scales https://arxiv.org/pdf/2212.09803.pdf☆22Updated 11 months ago
- Fine-Tuning Pre-trained Transformers into Decaying Fast Weights☆19Updated 2 years ago
- GPT, but made only out of MLPs☆86Updated 3 years ago
- Python implementation of "Data-dependent Learning of Symmetric/Antisymmetric Relations for Knowledge Base Completion [Manabe+. 2018]"☆11Updated 6 years ago
- Pretraining summarization models using a corpus of nonsense☆13Updated 3 years ago
- Code for paper "Do Language Models Have Beliefs? Methods for Detecting, Updating, and Visualizing Model Beliefs"☆28Updated 2 years ago
- Describing changes in LLM research trends in 2023. https://arxiv.org/abs/2307.10700☆15Updated 9 months ago
- Adding new tasks to T0 without catastrophic forgetting☆30Updated 2 years ago
- ☆12Updated 2 years ago
- A Jax implementation of word2vec's skip-gram model with negative sampling as described in Mikolov et al., 2013☆9Updated 3 weeks ago
- lanmt ebm☆11Updated 4 years ago