attract-repel
Vector refinement tool
An implementation of an algorithm to fine-tune word vector spaces with simple language-specific rules
The Attract-Repel algorithm presented in (Mrkšić et al., TACL 2017), with accompanying resources.
64 stars
9 watching
17 forks
Language: Python
last commit: about 7 years ago Related projects:
| Repository | Description | Stars |
|---|---|---|
| nmrksic/counter-fitting | A tool for modifying word vectors to conform to linguistic constraints | 144 |
 roboflow/maestro | A tool to streamline fine-tuning of multimodal models for vision-language tasks | 1,386 |
 nlprinceton/alacarte | Tools and code for inducing custom semantic vector representations from text data | 104 |
 xlearning-scu/2021-cvpr-mrl | Develops a robust learning framework to handle noisy labels in multimodal data and improve cross-modal retrieval. | 13 |
 ropensci/coordinatecleaner | Automated tool to detect and flag spatial and temporal errors in biological data | 79 |
 spandan-madan/pytorch_fine_tuning_tutorial | Provides guidance on fine-tuning pre-trained models for image classification tasks using PyTorch. | 279 |
 mfaruqui/non-distributional | Provides non-distributional word vector representations and tools to create them from linguistic lexicons | 62 |
 mzucker/maptrace | Generates vector maps by tracing raster images. | 123 |
 neuralmagic/sparseml | Enables the creation of smaller neural network models through efficient pruning and quantization techniques | 2,071 |
 lancopku/iais | This project proposes a novel method for calibrating attention distributions in multimodal models to improve contextualized representations of image-text pairs. | 30 |
 ys-zong/vlguard | Improves safety and helpfulness of large language models by fine-tuning them using safety-critical tasks | 45 |
 wasidennis/adaptsegnet | This project implements a deep learning-based approach to adapt semantic segmentation models from one domain to another. | 849 |
 mikeizbicki/herbieplugin | Improves numerical stability in Haskell code by automatically rewriting floating point computations. | 191 |
 ohtsukalab/autogenu-jupyter | An automatic code generator and solver for nonlinear model predictive control (NMPC) problems. | 155 |
 mmark-md/mmark | A markdown parser designed to produce high-quality error messages and offer extensions for customizing its behavior | 111 |