Natural Language Understanding on PDP60

Metric: Accuracy (higher is better)

LeaderboardDataset

Loading chart...

Results

Submit a result

#	Model↕	Accuracy▼	Extra Data	Paper	Date↕	Code
1	HNN	90	No	A Hybrid Neural Network Model for Commonsense Re...	2019-07-27	Code
2	BERT-large 340M	78.3	No	BERT: Pre-training of Deep Bidirectional Transfo...	2018-10-11	Code
3	UDSSM-II (ensemble)	78.3	No	Unsupervised Deep Structured Semantic Models for...	2019-04-03	-
4	UDSSM-I (ensemble)	76.7	No	Unsupervised Deep Structured Semantic Models for...	2019-04-03	-
5	DSSM	75	No	Unsupervised Deep Structured Semantic Models for...	2019-04-03	-
6	UDSSM-II	75	No	Unsupervised Deep Structured Semantic Models for...	2019-04-03	-
7	BERT-base 110M + MAS	68.3	No	Attention Is (not) All You Need for Commonsense ...	2019-05-31	Code
8	USSM + Supervised Deepnet + 3 Knowledge Bases	66.7	No	Attention Is (not) All You Need for Commonsense ...	2019-05-31	Code
9	Word-level CNN+LSTM (full scoring)	60	No	A Simple Method for Commonsense Reasoning	2018-06-07	Code
10	Subword-level Transformer LM	58.3	No	Attention Is All You Need	2017-06-12	Code
11	USSM + Cause-Effect Knowledge Base	55	No	Probabilistic Reasoning via Deep Learning: Neura...	2016-03-24	-
12	Word-level CNN+LSTM (partial scoring)	53.3	No	A Simple Method for Commonsense Reasoning	2018-06-07	Code
13	USSM + Supervised Deepnet	53.3	No	Attention Is (not) All You Need for Commonsense ...	2019-05-31	Code