RI-Medium: Collaborative Research: Dynamically-Structured Conditional Random Fields for Complex, Natural Domains

摘要近年来，生物信息学、自然语言理解、计算机视觉、信息检索等领域的研究取得了很大进展，条件随机场（CRFs）是一种结构化输出的机器学习模型，如序列、树和网格。然而，这些应用领域中的许多基本问题不仅涉及固定的结构，而且还涉及必须推断的结构。这种结构上的模糊性来自于不同层次的表达（例如，从字符序列到含义，或从像素到场景解释）的交互选择。该项目将把条件随机场（CRF）从固定的图形结构转移到在推理过程中动态构建的结构。这种能力将是构建下一代系统的关键，这些系统不仅可以解决问题的单个部分，还可以以统一的方式解决复杂的多步骤问题，如自然语言理解和计算机视觉中的问题。

Abstract Recent progress in bioinformatics, natural language understanding, computer vision, information retrieval and other areas has been significantly enabled by "conditional random fields" (CRFs)---machine learning models of structured outputs, such as sequences, trees and grids. However, many of the fundamental problems in these application areas involve not just fixed structures, but structures that must be inferred. This structural ambiguity arises from interacting choices at different levels of representation (e.g. from character sequences to meaning, or from pixels to scene interpretation). The project will move conditional random fields (CRFs) beyond fixed graphical structures to structures that are constructed dynamically during inference. Such a capability will be key to building next-generation systems that solve, not just an individual piece of a problem, but complex multi-step problems, as found in natural language understanding and computer vision, in a unified way.