Title Generation with Quasi-Synchronous Grammar
Title Generation with Quasi-Synchronous Grammar
复制标题
DOI：
--
复制
发表时间：
2010-10
影响因子：
6.6
通讯作者：
K. Woodsend;Yansong Feng;Mirella Lapata
中科院分区：
文献类型：
--
作者：
K. Woodsend;Yansong Feng;Mirella Lapata
选择信息并适当呈现它的任务在摘要中出现在多个上下文中。在本文中，我们提出了一个同时优化选择和呈现偏好的模型。该模型对源文档的基于短语的表示进行操作，我们通过合并PCFG解析树和依赖图来获得源文档。单个短语的选择偏好是有区别地学习的，而准同步语法（Smith and Eisner, 2006）捕获了诸如释义和压缩之类的呈现偏好。基于整数线性规划公式，该模型学习生成满足两种类型偏好的摘要，同时确保满足长度、主题覆盖和语法约束。对标题和图片标题生成的实验表明，我们的方法在没有任何重大修改的情况下，使用基本相同的模型获得了最先进的性能。
The task of selecting information and rendering it appropriately appears in multiple contexts in summarization. In this paper we present a model that simultaneously optimizes selection and rendering preferences. The model operates over a phrase-based representation of the source document which we obtain by merging PCFG parse trees and dependency graphs. Selection preferences for individual phrases are learned discriminatively, while a quasi-synchronous grammar (Smith and Eisner, 2006) captures rendering preferences such as paraphrases and compressions. Based on an integer linear programming formulation, the model learns to generate summaries that satisfy both types of preferences, while ensuring that length, topic coverage and grammar constraints are met. Experiments on headline and image caption generation show that our method obtains state-of-the-art performance using essentially the same model for both tasks without any major modifications.