Referring Expression Generation under Uncertainty: Algorithm and Evaluation Framework
Referring Expression Generation under Uncertainty: Algorithm and Evaluation Framework
复制标题
不确定性下的引用表达式生成：算法和评估框架
DOI：
10.18653/v1/w17-3511
复制
发表时间：
2017
影响因子：
3.8
通讯作者：
Matthias Scheutz
中科院分区：
文献类型：
--
作者：
T. Williams;Matthias Scheutz
为了使情境代理能够有效地与人类进行自然语言交互，他们必须能够引用诸如人、位置和物体之类的实体。虽然增量算法 (IA) 等经典指称表达式生成 (REG) 算法假设所有指称对象都有完美、完整且可访问的知识，但这并不总是可能的。在这项工作中，我们展示了如何使用先前提出的顾问框架（当知识不确定、异构和分布式时，有助于参考解析）来扩展 IA 以生成 DIST-PIA，这是一种在不确定、异构和分布式知识下的 REG 的域无关算法。我们还提出了一种新颖的框架，可用于评估此类 REG 算法，而无需将算法的性能与其所使用的分类器的性能混为一谈。
For situated agents to effectively engage in natural-language interactions with humans, they must be able to refer to entities such as people, locations, and objects. While classic referring expression generation (REG) algorithms like the Incremental Algorithm (IA) assume perfect, complete, and accessible knowledge of all referents, this is not always possible. In this work, we show how a previously presented consultant framework (which facilitates reference resolution when knowledge is uncertain, heterogeneous and distributed) can be used to extend the IA to produce DIST-PIA, a domain-independent algorithm for REG under uncertain, heterogeneous, and distributed knowledge. We also present a novel framework that can be used to evaluate such REG algorithms without conflating the performance of the algorithm with the performance of classifiers it employs.
DOI：
10.7551/mitpress/9082.001.0001
发表时间：
2016-04
期刊：
--
影响因子：
--
作者：
Kees van Deemter
通讯作者：
Kees van Deemter