Papers with Code · CC BY-SA 4.0

SNLI

아카이브 평가 98건 · 마지막 적재/변경 2026-10-30

평가 기록

과거 수집 기록이며 최신 순위가 아닙니다. 데이터셋 버전·split·실험 조건과 지표 방향이 검증되지 않은 결과는 직접 비교할 수 없습니다. 날짜는 논문 날짜이며 최신 평가일을 뜻하지 않습니다.

표가 화면보다 넓으면 좌우로 스크롤하여 논문과 구현 링크를 확인하세요.

원본 기록 순서 · 순위 미부여
모델	원본 지표·값	논문	구현
300D mLSTM word-by-word attention model	% Test Accuracy 86.1 % Train Accuracy 92.0 Parameters 1.9m	Learning Natural Language Inference with LSTM 2015-12-30	코드 1 · 코드 2 · 코드 3 · 코드 4
600D Gumbel TreeLSTM encoders	% Test Accuracy 86.0 % Train Accuracy 93.1 Parameters 10m	Learning to Compose Task-Specific Tree Structures 2017-07-10	코드 1
600D Residual stacked encoders	% Test Accuracy 86.0 % Train Accuracy 91.0 Parameters 29m	Shortcut-Stacked Sentence Encoders for Multi-Domain Inference 2017-08-07	코드 1 · 코드 2 · 코드 3
Star-Transformer (no cross sentence attention)	% Test Accuracy 86.0	Star-Transformer 2019-02-25	코드 1 · 코드 2
300D CAFE (no cross-sentence attention)	% Test Accuracy 85.9 % Train Accuracy 87.3 Parameters 3.7m	Compare, Compress and Propagate: Enhancing Neural Architectures with Alignment Factorization for Natural Language Inference 2017-12-30	연결 없음
1200D REGMAPR (Base+Reg)	% Test Accuracy 85.9 % Train Accuracy – Parameters –	연결 없음 논문 날짜 미기재	연결 없음
300D Residual stacked encoders	% Test Accuracy 85.7 % Train Accuracy 89.8 Parameters 9.7m	Shortcut-Stacked Sentence Encoders for Multi-Domain Inference 2017-08-07	코드 1 · 코드 2 · 코드 3
300D LSTMN with deep attention fusion	% Test Accuracy 85.7 % Train Accuracy 87.3 Parameters 1.7m	Long Short-Term Memory-Networks for Machine Reading 2016-01-25	코드 1 · 코드 2 · 코드 3
300D Gumbel TreeLSTM encoders	% Test Accuracy 85.6 % Train Accuracy 91.2 Parameters 2.9m	Learning to Compose Task-Specific Tree Structures 2017-07-10	코드 1
300D Directional self-attention network encoders	% Test Accuracy 85.6 % Train Accuracy 91.1 Parameters 2.4m	DiSAN: Directional Self-Attention Network for RNN/CNN-Free Language Understanding 2017-09-14	코드 1 · 코드 2 · 코드 3
600D (300+300) Deep Gated Attn. BiLSTM encoders	% Test Accuracy 85.5 % Train Accuracy 90.5 Parameters 12m	Recurrent Neural Network-Based Sentence Encoder with Gated Attention for Natural Language Inference 2017-08-04	코드 1 · 코드 2
300D MMA-NSE encoders with attention	% Test Accuracy 85.4 % Train Accuracy 86.9 Parameters 3.2m	Neural Semantic Encoders 2016-07-14	코드 1 · 코드 2 · 코드 3
50D stacked TC-LSTMs	% Test Accuracy 85.1 % Train Accuracy 86.7 Parameters 190k	Modelling Interaction of Sentence Pair with coupled-LSTMs 2016-05-18	연결 없음
600D (300+300) BiLSTM encoders with intra-attention and symbolic preproc.	% Test Accuracy 85.0 % Train Accuracy 85.9 Parameters 2.8m	Learning Natural Language Inference using Bidirectional LSTM model and Inner-Attention 2016-05-30	코드 1 · 코드 2
Stacked Bi-LSTMs (shortcut connections, max-pooling)	% Test Accuracy 84.8	Combining Similarity Features and Deep Representation Learning for Stance Detection in the Context of Checking Fake News 2018-11-02	코드 1 · 코드 2 · 코드 3
300D NSE encoders	% Test Accuracy 84.6 % Train Accuracy 86.2 Parameters 3.0m	Neural Semantic Encoders 2016-07-14	코드 1 · 코드 2 · 코드 3
100D DF-LSTM	% Test Accuracy 84.6 % Train Accuracy 85.2 Parameters 320k	Deep Fusion LSTMs for Text Semantic Matching 2016-08-01	연결 없음
4096D BiLSTM with max-pooling	% Test Accuracy 84.5 % Train Accuracy 85.6 Parameters 40m	Supervised Learning of Universal Sentence Representations from Natural Language Inference Data 2017-05-05	코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 · 코드 6 · 코드 7 · 코드 8 · 코드 9 · 코드 10 · 코드 11 · 코드 12 · 코드 13 · 코드 14 · 코드 15 · 코드 16 · 코드 17 · 코드 18 · 코드 19 · 코드 20 · 코드 21 · 코드 22 · 코드 23
Bi-LSTM sentence encoder (max-pooling)	% Test Accuracy 84.5	Combining Similarity Features and Deep Representation Learning for Stance Detection in the Context of Checking Fake News 2018-11-02	코드 1 · 코드 2 · 코드 3
Stacked Bi-LSTMs (shortcut connections, max-pooling, attention)	% Test Accuracy 84.4	Combining Similarity Features and Deep Representation Learning for Stance Detection in the Context of Checking Fake News 2018-11-02	코드 1 · 코드 2 · 코드 3
600D (300+300) BiLSTM encoders with intra-attention	% Test Accuracy 84.2 % Train Accuracy 84.5 Parameters 2.8m	Learning Natural Language Inference using Bidirectional LSTM model and Inner-Attention 2016-05-30	코드 1 · 코드 2
SWEM-max	% Test Accuracy 83.8	Baseline Needs More Love: On Simple Word-Embedding-Based Models and Associated Pooling Mechanisms 2018-05-24	코드 1 · 코드 2
100D LSTMs w/ word-by-word attention	% Test Accuracy 83.5 % Train Accuracy 85.3 Parameters 250k	Reasoning about Entailment with Neural Attention 2015-09-22	코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 · 코드 6 · 코드 7
300D NTI-SLSTM-LSTM encoders	% Test Accuracy 83.4 % Train Accuracy 82.5 Parameters 4.0m	Neural Tree Indexers for Text Understanding 2016-07-15	코드 1
600D (300+300) BiLSTM encoders	% Test Accuracy 83.3 % Train Accuracy 86.4 Parameters 2.0m	Learning Natural Language Inference using Bidirectional LSTM model and Inner-Attention 2016-05-30	코드 1 · 코드 2
300D SPINN-PI encoders	% Test Accuracy 83.2 % Train Accuracy 89.2 Parameters 3.7m	A Fast Unified Model for Parsing and Sentence Understanding 2016-03-19	코드 1 · 코드 2 · 코드 3
300D Tree-based CNN encoders	% Test Accuracy 82.1 % Train Accuracy 83.3 Parameters 3.5m	Natural Language Inference by Tree-Based Convolution and Heuristic Matching 2015-12-28	연결 없음
1024D GRU encoders w/ unsupervised 'skip-thoughts' pre-training	% Test Accuracy 81.4 % Train Accuracy 98.8 Parameters 15m	Order-Embeddings of Images and Language 2015-11-19	코드 1 · 코드 2
DELTA (LSTM)	% Test Accuracy 80.7	DELTA: A DEep learning based Language Technology plAtform 2019-08-02	코드 1 · 코드 2
300D LSTM encoders	% Test Accuracy 80.6 % Train Accuracy 83.9 Parameters 3.0m	A Fast Unified Model for Parsing and Sentence Understanding 2016-03-19	코드 1 · 코드 2 · 코드 3