NeuroQL: A Neuro-Symbolic Language and Dataset for Inter-Subjective Reasoning
This addresses the challenge of integrating symbolic and neural reasoning for AI systems dealing with mixed objective-subjective information, though it appears incremental as it builds on existing neuro-symbolic approaches.
The paper tackles the problem of inter-subjective reasoning, which involves combining objective facts with subjective user reviews, by introducing NeuroQL, a neuro-symbolic language and dataset that enables automatic translation of natural language questions into executable code for answering such queries.
We present a new AI task and baseline solution for Inter-Subjective Reasoning. We define inter-subjective information, to be a mixture of objective and subjective information possibly shared by different parties. Examples may include commodities and their objective properties as reported by IR (Information Retrieval) systems, that need to be cross-referenced with subjective user reviews from an online forum. For an AI system to successfully reason about both, it needs to be able to combine symbolic reasoning of objective facts with the shared consensus found on subjective user reviews. To this end we introduce the NeuroQL dataset and DSL (Domain-specific Language) as a baseline solution for this problem. NeuroQL is a neuro-symbolic language that extends logical unification with neural primitives for extraction and retrieval. It can function as a target for automatic translation of inter-subjective questions (posed in natural language) into the neuro-symbolic code that can answer them.