Tasks
SotA
Datasets
Papers
Methods
Submit
About
Datasets
/
PEN
PEN
Problems with Explanations for Numbers
Introduced 2022-05-01
Provided explanations on the existing three benchmark datasets on solving algebraic word problems: ALG514, DRAW-1K, MAWPS
Benchmarks
Math Word Problem Solving
/
Accuracy (%)
Mathematical Question Answering
/
Accuracy (%)
Mathematical Reasoning
/
Accuracy (%)
Question Answering
/
Accuracy (%)
Related Benchmarks
PenDigits
/
Time Series Classification
/
Accuracy
PenDigits
/
Time Series Classification
/
NLL
Pendulum-v1
/
OpenAI Gym
/
Action Repetition
Pendulum-v1
/
OpenAI Gym
/
Average Decisions
Pendulum-v1
/
OpenAI Gym
/
Mean Reward
Penn Action
/
Action Recognition
/
Accuracy
Penn Action
/
Activity Recognition
/
Accuracy
Penn Treebank
/
Chunking
/
F1 score
Penn Treebank
/
Constituency Parsing
/
F1 score
Penn Treebank
/
Dependency Parsing
/
LAS
Penn Treebank
/
Dependency Parsing
/
POS
Penn Treebank
/
Dependency Parsing
/
UAS
Penn Treebank
/
Open Information Extraction
/
AUC
Penn Treebank
/
Open Information Extraction
/
F1
Penn Treebank
/
Part-Of-Speech Tagging
/
Accuracy
Penn Treebank
/
Shallow Syntax
/
F1 score
Penn Treebank (Character Level)
/
Language Modelling
/
Bit per Character (BPC)
Penn Treebank (Character Level)
/
Language Modelling
/
Number of params
Penn Treebank (Character Level) 3x1000 LSTM - 500 Epochs
/
Stochastic Optimization
/
Bit per Character (BPC)
Penn Treebank (Word Level)
/
Language Modelling
/
Params
Penn Treebank (Word Level)
/
Language Modelling
/
Test perplexity
Penn Treebank (Word Level)
/
Language Modelling
/
Validation perplexity
Penn94
/
Node Classification
/
1:1 Accuracy
Penn94
/
Node Classification
/
Accuracy
pendigits
/
Image Clustering
/
Accuracy
pendigits
/
Image Clustering
/
NMI
pendigits
/
Image/Document Clustering
/
Accuracy (%)
pendigits
/
Image/Document Clustering
/
NMI
pendigits
/
Image/Document Clustering
/
runtime (s)
pendigits
/
Time Series Classification
/
Accuracy
pendulum.swingup
/
3D
/
Return
pendulum.swingup
/
3D Face Modelling
/
Return
pendulum.swingup
/
Continuous Control
/
Return