软线性约束学习及其在引文领域抽取中的应用
Learning Soft Linear Constraints with Application to Citation Field Extraction
摘要:
准确地将引文字符串分割成作者、标题等字段是一项具有挑战性的任务,因为输出通常遵守各种全局约束。以前的工作已经表明,建模软约束,鼓励模型,但不要求遵守的约束,可以大大提高分割性能。另一方面,对于施加硬约束,对偶分解是一种流行的技术,用于有效的预测,给出现有的无约束推理算法。我们扩展的技术进行预测软约束。此外,通过在给定软约束的情况下进行推理的技术,可以很容易地自动生成大量约束,并在训练期间通过简单的凸优化问题来学习它们的成本。这使我们能够在一个新的、具有挑战性的引文提取数据集上获得大量的准确性。
英文摘要:
Accurately segmenting a citation string into fields for authors, titles, etc. is a challenging task because the output typically obeys various global constraints. Previous work has shown that modeling soft constraints, where the model is encouraged, but not require to obey the constraints, can substantially improve segmentation performance. On the other hand, for imposing hard constraints, dual decomposition is a popular technique for efficient prediction given existing algorithms for unconstrained inference. We extend the technique to perform prediction subject to soft constraints. Moreover, with a technique for performing inference given soft constraints, it is easy to automatically generate large families of constraints and learn their costs with a simple convex optimization problem during training. This allows us to obtain substantial gains in accuracy on a new, challenging citation extraction dataset.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。