Research map / Architectures and efficiency / RNNs and normalization
Siamese Recurrent Architectures for Learning Sentence Similarity
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add regression calibration (ablation) | MaLSTM · SICK relatedness test | Pearson r: 0.01 | Helped |
| add pre-training on SemEval 2013 STS data (ablation) | MaLSTM · SICK relatedness test | Pearson r: 0.02 | Helped |
| add synonym augmentation (ablation) | MaLSTM · SICK relatedness test | Pearson r: 0.04 | Helped |
| use multi-layer or bidirectional LSTMs (ablation) | MaLSTM · SICK relatedness test | Pearson r | No clear effect |
| siamese LSTM with Manhattan similarity instead of Tree-LSTM | sentence similarity models · SICK relatedness test | Pearson r: 0.8676 -> 0.8822 | Helped |
| use MaLSTM features with SVM instead of handcrafted features | entailment classification · SICK entailment test | accuracy: 84.6 -> 84.2 | Hurt |
Closest papers by meaning
- Few Shot Transfer Learning BetweenWord Relatedness and Similarity Tasks Using A Gated Recurrent Siamese Network (AAAI 2018 · similarity 0.89)
- Generalization through Memorization: Nearest Neighbor Language Models (ICLR 2020 · similarity 0.88)
- Scalable Attentive Sentence Pair Modeling via Distilled Sentence Embedding (AAAI 2020 · similarity 0.88)
- A Deep Architecture for Semantic Matching with Multiple Positional Sentence Representations (AAAI 2016 · similarity 0.88)
- Narrowing the Gap between Supervised and Unsupervised Sentence Representation Learning with Large Language Model (AAAI 2024 · similarity 0.86)
- RAT: Bridging RNN Efficiency and Attention Accuracy via Chunk-based Sequence Modeling (NeurIPS 2025 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.