Siamese Networks for Semantic Pattern Similarity
This addresses a niche NLP problem for database question answering, but it is incremental as it applies an existing method to a specific scenario.
The paper tackled the task of semantic pattern similarity for comparing sentences by abstract patterns, using Siamese Networks to determine SQL patterns for unseen questions in database-backed question answering, achieving high accuracy with a built-in confidence proxy to maintain precision.
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.