Evaluating algorithms for the Generation of Referring Expressions using a balanced corpus
Evaluating algorithms for the Generation of Referring Expressions using a balanced corpus
复制标题
使用平衡语料库评估引用表达式生成算法
DOI：
10.3115/1610163.1610172
复制
发表时间：
2007
期刊：
影响因子：
--
通讯作者：
Kees van Deemter
中科院分区：
文献类型：
--
作者：
Albert Gatt;Ielka van der Sluis;Kees van Deemter
尽管是密集研究的重点，但对产生参考表达式的算法的评估仍处于起步阶段。我们描述了一种基于语料库的评估方法，该方法应用于该领域的许多经典算法。该方法的重点是平衡和语义透明度，以比较人类和算法输出。尽管增量算法是最佳匹配，但我们发现其对手动集合参数的依赖性使其性能难以预测。
Despite being the focus of intensive research, evaluation of algorithms that generate referring expressions is still in its infancy. We describe a corpus-based evaluation methodology, applied to a number of classic algorithms in this area. The methodology focuses on balance and semantic transparency to enable comparison of human and algorithmic output. Although the Incremental Algorithm emerges as the best match, we found that its dependency on manually-set parameters makes its performance difficult to predict.