DIRT @SBT@discovery of inference rules from text
2001pp. 323–328
Citations Over TimeTop 10% of 2001 papers
Abstract
In this paper, we propose an unsupervised method for discovering inference rules from text, such as is author of Y a X wrote Y, solved Y a X found a solution to Y, and caused Y a Y is triggered by X. Inference rules are extremely important in many fields such as natural language processing, information retrieval, and artificial intelligence in general. Our algorithm is based on an extended version of Harris' Distributional Hypothesis, which states that words that occurred in the same contexts tend to be similar. Instead of using this hypothesis on words, we apply it to paths in the dependency trees of a parsed corpus.
Related Papers
- → From the Inference System Suitable for Human to the Inference System Suitable for Computer(2008)1 cited
- → The Linked Inference Principle, II: The User’s Viewpoint(1984)32 cited
- → The Nature of Induction(1979)1 cited
- Presenting and Combining Inference Systems: Presentations with Inference Rules.(2002)
- → Application of first-order logic to identify organizers and perpetrators of illegal actions in teams of a limited circle of people(2021)