Enhanced LSTM for Natural Language Inference

@inproceedings{Chen2017EnhancedLF,
  title={Enhanced LSTM for Natural Language Inference},
  author={Qian Chen and Xiao-Dan Zhu and Zhen-Hua Ling and Si Wei and Hui Jiang and Diana Inkpen},
  booktitle={ACL},
  year={2017}
}
(1) Handcrafted features [BAPM15] 78.2 (2) LSTM [BGR+16] 80.6 (3) GRU [VKFU15] 81.4 (4) Tree CNN [MML+16] 82.1 (5) SPINN-PI [BGR+16] 83.2 (6) BiLSTM intra-Att [LSLW16] 84.2 (7) NSE [MY16a] 84.6 (8) Att-LSTM [RGH+15] 83.5 (9) mLSTM [WJ16] 86.1 (10) LSTMN [CDL16] 86.3 (11) Decomposable Att [PTDU16] 86.3 (12) Intra-sent Att+(11) [PTDU16] 86.8 (13) NTI-SLSTM-LSTM [MY16b] 87.3 (14) Re-read LSTM [SCSL16] 87.5 (15) btree-LSTM [PAD+16] 87.6 

Figures, Tables, and Topics from this paper.

Explore Further: Topics Discussed in This Paper

Citations

Publications citing this paper.
SHOWING 1-10 OF 155 CITATIONS, ESTIMATED 44% COVERAGE

CAM: A Combined Attention Model for Natural Language Inference

  • 2018 IEEE International Conference on Big Data (Big Data)
  • 2018
VIEW 12 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

DR-BiLSTM: Dependent Reading Bidirectional LSTM for Natural Language Inference

  • NAACL-HLT
  • 2018
VIEW 11 EXCERPTS
CITES BACKGROUND, METHODS & RESULTS
HIGHLY INFLUENCED

Lessons from Natural Language Inference in the Clinical Domain

VIEW 12 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Multi-turn Inference Matching Network for Natural Language Inference

VIEW 14 EXCERPTS
CITES METHODS & RESULTS
HIGHLY INFLUENCED

R3: Reinforced Ranker-Reader for Open-Domain Question Answering

  • AAAI
  • 2018
VIEW 12 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

SWAG: A Large-Scale Adversarial Dataset for Grounded Commonsense Inference

VIEW 9 EXCERPTS
CITES BACKGROUND, METHODS & RESULTS
HIGHLY INFLUENCED

Towards Dynamic Computation Graphs via Sparse Latent Structure

VIEW 11 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Combining Fact Extraction and Verification with Neural Semantic Matching Networks

VIEW 8 EXCERPTS
CITES RESULTS, METHODS & BACKGROUND
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2017
2019

CITATION STATISTICS

  • 63 Highly Influenced Citations

  • Averaged 59 Citations per year over the last 3 years

  • 83% Increase in citations per year in 2018 over 2017

References

Publications referenced by this paper.
SHOWING 1-10 OF 39 REFERENCES

Similar Papers

Loading similar papers…