Stochastic and-or Grammars: A Unified Framework and Logic Perspective
Authors: Kewei Tu
IJCAI 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | In this paper we propose a representation framework of stochastic AOGs that is agnostic to the type of the data being modeled and thus unifies various domain-specific AOGs. Many existing grammar formalisms and probabilistic models in natural language processing, computer vision, and machine learning can be seen as special cases of this framework. We also propose a domain-independent inference algorithm of stochastic context-free AOGs and show its tractability under a reasonable assumption. Furthermore, we provide two interpretations of stochastic context-free AOGs as a subset of probabilistic logic, which connects stochastic AOGs to the field of statistical relational learning and clarifies their relation with a few existing statistical relational models. |
| Researcher Affiliation | Academia | Kewei Tu School of Information Science and Technology Shanghai Tech University, Shanghai, China tukw@shanghaitech.edu.cn |
| Pseudocode | Yes | Algorithm 1: Parsing with a stochastic context-free AOG |
| Open Source Code | No | The paper mentions supplementary material but does not explicitly state that source code for the methodology is available or provide a link to a code repository. The supplementary material link provided is for a PDF document containing more proofs. |
| Open Datasets | No | The paper discusses concepts related to data samples (e.g., "text data", "image data") in the context of its theoretical framework, but it does not specify any particular dataset used for training or provide access information for a public dataset. |
| Dataset Splits | No | The paper is theoretical and proposes an algorithm; it does not report on experiments with data splits for training, validation, or testing. |
| Hardware Specification | No | The paper does not mention any specific hardware used, as it focuses on theoretical contributions and algorithm design rather than empirical experimentation. |
| Software Dependencies | No | The paper does not list specific software dependencies with version numbers, as it is a theoretical work and does not describe an implementation's environment. |
| Experiment Setup | No | The paper proposes a theoretical framework and algorithm. It does not describe any specific experimental setup details, hyperparameters, or training configurations, as it does not report on empirical experiments. |