Neural Logic Analogy Learning

• URL: http://arxiv.org/abs/2202.02436v1
• Date: Fri, 4 Feb 2022 23:35:53 GMT
• Title: Neural Logic Analogy Learning
• Authors: Yujia Fan and Yongfeng Zhang
• Abstract summary: Letter-string analogy is an important analogy learning task which seems to be easy for humans but challenging for machines. In this paper, we propose Neural logic analogy learning (Noan), which is a dynamic neural architecture driven by differentiable logic reasoning. Noan learns the logical variables as vector embeddings and learns each logical operation as a neural module.
• Score: 33.424692414746836
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Letter-string analogy is an important analogy learning task which seems to be easy for humans but very challenging for machines. The main idea behind current approaches to solving letter-string analogies is to design heuristic rules for extracting analogy structures and constructing analogy mappings. However, one key problem is that it is difficult to build a comprehensive and exhaustive set of analogy structures which can fully describe the subtlety of analogies. This problem makes current approaches unable to handle complicated letter-string analogy problems. In this paper, we propose Neural logic analogy learning (Noan), which is a dynamic neural architecture driven by differentiable logic reasoning to solve analogy problems. Each analogy problem is converted into logical expressions consisting of logical variables and basic logical operations (AND, OR, and NOT). More specifically, Noan learns the logical variables as vector embeddings and learns each logical operation as a neural module. In this way, the model builds computational graph integrating neural network with logical reasoning to capture the internal logical structure of the input letter strings. The analogy learning problem then becomes a True/False evaluation problem of the logical expressions. Experiments show that our machine learning-based Noan approach outperforms state-of-the-art approaches on standard letter-string analogy benchmark datasets.

Related papers

• Language Models can be Logical Solvers [99.40649402395725]
  We introduce LoGiPT, a novel language model that directly emulates the reasoning processes of logical solvers. LoGiPT is fine-tuned on a newly constructed instruction-tuning dataset derived from revealing and refining the invisible reasoning process of deductive solvers.
  arXiv  Detail & Related papers  (2023-11-10T16:23:50Z)
• Empower Nested Boolean Logic via Self-Supervised Curriculum Learning [67.46052028752327]
  We find that any pre-trained language models even including large language models only behave like a random selector in the face of multi-nested logic. To empower language models with this fundamental capability, this paper proposes a new self-supervised learning method textitCurriculum Logical Reasoning (textscClr)
  arXiv  Detail & Related papers  (2023-10-09T06:54:02Z)
• LOGICSEG: Parsing Visual Semantics with Neural Logic Learning and Reasoning [73.98142349171552]
  LOGICSEG is a holistic visual semantic that integrates neural inductive learning and logic reasoning with both rich data and symbolic knowledge. During fuzzy logic-based continuous relaxation, logical formulae are grounded onto data and neural computational graphs, hence enabling logic-induced network training. These designs together make LOGICSEG a general and compact neural-logic machine that is readily integrated into existing segmentation models.
  arXiv  Detail & Related papers  (2023-09-24T05:43:19Z)
• Discourse-Aware Graph Networks for Textual Logical Reasoning [142.0097357999134]
  Passage-level logical relations represent entailment or contradiction between propositional units (e.g., a concluding sentence) We propose logic structural-constraint modeling to solve the logical reasoning QA and introduce discourse-aware graph networks (DAGNs) The networks first construct logic graphs leveraging in-line discourse connectives and generic logic theories, then learn logic representations by end-to-end evolving the logic relations with an edge-reasoning mechanism and updating the graph features.
  arXiv  Detail & Related papers  (2022-07-04T14:38:49Z)
• Logiformer: A Two-Branch Graph Transformer Network for Interpretable Logical Reasoning [10.716971124214332]
  We propose an end-to-end model Logiformer which utilizes a two-branch graph transformer network for logical reasoning of text. We introduce different extraction strategies to split the text into two sets of logical units, and construct the logical graph and the syntax graph respectively. The reasoning process provides the interpretability by employing the logical units, which are consistent with human cognition.
  arXiv  Detail & Related papers  (2022-05-02T08:34:59Z)
• Scales and Hedges in a Logic with Analogous Semantics [0.0]
  Fuzzy Logic has a number of explanatory and application advantages, the most well-known being the ability to help experts develop control systems. For social decision making in humans, it is vital that logical conclusions about others are grounded in empathic emotion. This paper adds to the existing theory how scales, as necessary for adjective and verb semantics can be handled by the system.
  arXiv  Detail & Related papers  (2022-01-21T12:48:58Z)
• On syntactically similar logic programs and sequential decompositions [0.0]
  Rule-based reasoning is an essential part of human intelligence prominently formalized in artificial intelligence research via logic programs. Describing complex objects as the composition of elementary ones is a common strategy in computer science and science in general. We show how similarity can be used to answer queries across different domains via a one-step reduction.
  arXiv  Detail & Related papers  (2021-09-11T15:22:17Z)
• Logic-Driven Context Extension and Data Augmentation for Logical Reasoning of Text [65.24325614642223]
  We propose to understand logical symbols and expressions in the text to arrive at the answer. Based on such logical information, we put forward a context extension framework and a data augmentation algorithm. Our method achieves the state-of-the-art performance, and both logic-driven context extension framework and data augmentation algorithm can help improve the accuracy.
  arXiv  Detail & Related papers  (2021-05-08T10:09:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.