Research map / Architectures and efficiency / Attention and transformers
A Deep Architecture for Semantic Matching with Multiple Positional Sentence Representations
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 |
|---|---|---|---|
| match with multiple positional Bi-LSTM representations instead of last-position LSTM representation | LSTM-RNN · Yahoo! Answers QA | P@1: 0.690 -> 0.766 | Helped |
| use tensor layer instead of cosine interaction (ablation) | MV-LSTM · Yahoo! Answers QA | P@1: 0.739 -> 0.766 | Helped |
| use tensor layer instead of cosine interaction (ablation) | MV-LSTM · Reuters sentence completion | P@1: 0.665 -> 0.691 | Helped |
| increase k-max pooling k from 1 to 5 (ablation) | MV-LSTM-Cosine · Yahoo! Answers QA | P@1: 0.726 -> 0.739 | Helped |
| increase k from 5 to 10 (ablation) | MV-LSTM-Cosine · Yahoo! Answers QA | P@1: 0.739 -> 0.740 | No clear effect |
| MV-LSTM-Tensor vs multi-granularity MultiGranCNN | semantic matching · Reuters sentence completion | P@1: 0.595 -> 0.691 | Helped |
Closest papers by meaning
- Semantic Sentence Matching with Densely-Connected Recurrent and Co-Attentive Information (AAAI 2019 · similarity 0.88)
- Siamese Recurrent Architectures for Learning Sentence Similarity (AAAI 2016 · similarity 0.88)
- Narrowing the Gap between Supervised and Unsupervised Sentence Representation Learning with Large Language Model (AAAI 2024 · similarity 0.85)
- Multi-Pair Temporal Sentence Grounding via Multi-Thread Knowledge Transfer Network (AAAI 2025 · similarity 0.84)
- Prompt Compression with Context-Aware Sentence Encoding for Fast and Improved LLM Inference (AAAI 2025 · similarity 0.83)
- Overcoming Long Context Limitations of State Space Models via Context Dependent Sparse Attention (NeurIPS 2025 · similarity 0.83)
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.