rowanz / Swagaf
Licence: mit
Repository for paper "SWAG: A Large-Scale Adversarial Dataset for Grounded Commonsense Inference"
Stars: ✭ 156
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Swagaf
Tree Transformer
Implementation of the paper Tree Transformer
Stars: ✭ 148 (-5.13%)
Mutual labels: natural-language-processing
Chineseblue
Chinese Biomedical Language Understanding Evaluation benchmark (ChineseBLUE)
Stars: ✭ 149 (-4.49%)
Mutual labels: natural-language-processing
Natural Language Processing Specialization
This repo contains my coursework, assignments, and Slides for Natural Language Processing Specialization by deeplearning.ai on Coursera
Stars: ✭ 151 (-3.21%)
Mutual labels: natural-language-processing
Pycantonese
Cantonese Linguistics and NLP in Python
Stars: ✭ 147 (-5.77%)
Mutual labels: natural-language-processing
Spacymoji
💙 Emoji handling and meta data for spaCy with custom extension attributes
Stars: ✭ 151 (-3.21%)
Mutual labels: natural-language-processing
Postagga
A Library to parse natural language in pure Clojure and ClojureScript
Stars: ✭ 152 (-2.56%)
Mutual labels: natural-language-processing
Words counted
A Ruby natural language processor.
Stars: ✭ 146 (-6.41%)
Mutual labels: natural-language-processing
Pythonrouge
Python wrapper for evaluating summarization quality by ROUGE package
Stars: ✭ 155 (-0.64%)
Mutual labels: natural-language-processing
Finnlp Progress
NLP progress in Fintech. A repository to track the progress in Natural Language Processing (NLP) related to the domain of Finance, including the datasets, papers, and current state-of-the-art results for the most popular tasks.
Stars: ✭ 148 (-5.13%)
Mutual labels: natural-language-processing
Dialogflow Ruby Client
Ruby SDK for Dialogflow
Stars: ✭ 148 (-5.13%)
Mutual labels: natural-language-processing
Spacy Course
👩🏫 Advanced NLP with spaCy: A free online course
Stars: ✭ 1,920 (+1130.77%)
Mutual labels: natural-language-processing
Chemdataextractor
Automatically extract chemical information from scientific documents
Stars: ✭ 152 (-2.56%)
Mutual labels: natural-language-processing
Negapoji
Japanese negative positive classification.日本語文書のネガポジを判定。
Stars: ✭ 148 (-5.13%)
Mutual labels: natural-language-processing
Pytorch Question Answering
Important paper implementations for Question Answering using PyTorch
Stars: ✭ 154 (-1.28%)
Mutual labels: natural-language-processing
Turkce Yapay Zeka Kaynaklari
Türkiye'de yapılan derin öğrenme (deep learning) ve makine öğrenmesi (machine learning) çalışmalarının derlendiği sayfa.
Stars: ✭ 1,900 (+1117.95%)
Mutual labels: natural-language-processing
Crf Layer On The Top Of Bilstm
The CRF Layer was implemented by using Chainer 2.0. Please see more details here: https://createmomo.github.io/2017/09/12/CRF_Layer_on_the_Top_of_BiLSTM_1/
Stars: ✭ 148 (-5.13%)
Mutual labels: natural-language-processing
Rnn lstm from scratch
How to build RNNs and LSTMs from scratch with NumPy.
Stars: ✭ 156 (+0%)
Mutual labels: natural-language-processing
Paraphrase identification
Examine two sentences and determine whether they have the same meaning.
Stars: ✭ 154 (-1.28%)
Mutual labels: natural-language-processing
swagaf
visualcommonsense.com!
Like this work, or commonsense reasoning in general? You might be interested in checking out my brand new dataset VCR: Visual Commonsense Reasoning, atSWAG dataset. More info is at rowanzellers.com/swag.
Setting up your environment
To create an environment you will need to intall Python 3.1, PyTorch 3.1, and AllenNLP. These
requirements are listed in requirements.txt
.
You will also need to set PYTHONPATH to the swagaf
directory. You can do this by running the
following command from the swagaf
folder.
export PYTHONPATH=$(pwd)
Alternatively, you can build and run the included Dockerfile to create an environment.
docker build -t swagaf .
docker run -it swagaf
Common use cases
There is additional documentation in the subfolders.
-
data/
contains the SWAG dataset. -
swag_baslines/
contains baseline implementations and instructions for how to run them.
Most people will not need to look at create_swag
or raw_data
but it's there if you need it!
Citing
@inproceedings{zellers2018swagaf,
title={SWAG: A Large-Scale Adversarial Dataset for Grounded Commonsense Inference},
author={Zellers, Rowan and Bisk, Yonatan and Schwartz, Roy and Choi, Yejin},
booktitle = "Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP)",
year={2018}
}
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].