Siamese Networks for Semantic Pattern Similarity

2018/12/17 by Yassine Benajiba, Benajiba, Yassine, Jin Sun +9
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Natural Language Processing Techniques #Speech and dialogue systems #Topic Modeling

paper · pdf · doi:10.48550/arxiv.1812.06604

openalex publication_date 2018/12/17 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Semantic Pattern Similarity is an interesting, though not often encountered NLP task where two sentences are compared not by their specific meaning, but by their more abstract semantic pattern (e.g., preposition or frame). We utilize Siamese Networks to model this task, and show its usefulness in determining SQL patterns for unseen questions in a database-backed question answering scenario. Our approach achieves high accuracy and contains a built-in proxy for confidence, which can be used to keep precision arbitrarily high.

Citations

• Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning
• Generating Sentences by Editing Prototypes

Related

• Siamese Neural Networks with Random Forest for detecting duplicate question pairs
• Predicting the Semantic Textual Similarity with Siamese CNN and LSTM
• A Distribution-Based Threshold for Determining Sentence Similarity
• Chinese Sentences Similarity via Cross-Attention Based Siamese Network
• Injecting Relational Structural Representation in Neural Networks for\n Question Similarity