https://github.com/blester125/multi-look-embeddings
Code for exploring why multiple embeddings work well
Science Score: 10.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
○CITATION.cff file
-
○codemeta.json file
-
○.zenodo.json file
-
○DOI references
-
✓Academic publication links
Links to: arxiv.org -
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (5.4%) to scientific vocabulary
Last synced: 10 months ago
·
JSON representation
Repository
Code for exploring why multiple embeddings work well
Basic Info
- Host: GitHub
- Owner: blester125
- Language: Python
- Default Branch: master
- Size: 38.1 KB
Statistics
- Stars: 1
- Watchers: 2
- Forks: 0
- Open Issues: 1
- Releases: 0
Created about 6 years ago
· Last pushed over 5 years ago
https://github.com/blester125/multi-look-embeddings/blob/master/
# Multi Look Embeddings
Code used for experiments from [Multiple Word Embeddings for Increased Diversity of Representation](https://arxiv.org/abs/2009.14394)
Some scripts, utils, and [mead-baseline](https://github.com/dpressel/mead-baseline) configs for probing *why* multiple embeddings work.
Scripts should be run from the top level of this repo with `python -m scripts.{script_name}`
Train mead-baseline models with `mead-train --config configs/sst2.json`
# Citation
If you use this multiple embedding technique or any of these analysis tools in your research please cite the following:
```BibTex
@article{lester-2020-multiple,
title={Multiple Word Embeddings for Increased Diversity of Representation},
author={Lester, Brian and Pressel, Daniel and Hemmeter, Amy and Choudhury, Sagnik Ray and Bangalore, Srinivas},
journal={arXiv preprint arXiv:2009.14394},
year={2020}
}
```
Owner
- Name: Brian Lester
- Login: blester125
- Kind: user
- Website: blester125.com
- Repositories: 23
- Profile: https://github.com/blester125
GitHub Events
Total
Last Year
Dependencies
requirements.txt
pypi
- faiss *
- file_or_name *
- mead-baseline *
- numpy *
- tabulate *
- tensorflow >=2.0.0
- torch >=1.3
- word_vectors *