An Orthonormal Basis for Topic Segmentation in Tutorial Dialogue

An Orthonormal Basis for Topic Segmentation in Tutorial Dialogue
复制标题

教程对话中主题分割的正交基础

DOI:
10.3115/1220575.1220697
复制
发表时间:
2005
影响因子:
2.5
通讯作者:
Zhiqiang Cai
Zhiqiang Cai
中科院分区:
心理学3区
文献类型:
--
作者:
A. Olney;Zhiqiang Cai

文献摘要

参考文献

被引文献

相似文献

本文探讨了教学对话的分割为衔接话题。一个潜在的语义空间创建使用从人到人的辅导成绩单的对话,允许使用向量相似性来测量话语之间的衔接。以前的基于内聚的分割方法,专注于短暂的独白重新应用到这些对话,以创建性能的基准。一种新的移动窗口技术,使用正交基的语义向量显着优于这些基准上的对话分割任务。
This paper explores the segmentation of tutorial dialogue into cohesive topics. A latent semantic space was created using conversations from human to human tutoring transcripts, allowing cohesion between utterances to be measured using vector similarity. Previous cohesion-based segmentation methods that focus on expository monologue are reapplied to these dialogues to create benchmarks for performance. A novel moving window technique using orthonormal bases of semantic vectors significantly outperforms these benchmarks on this dialogue segmentation task.
DOI: 10.1080/01638539809545028
发表时间: 1998-01-01
影响因子: 2.2
作者:
Landauer, TK;Foltz, PW;Laham, D
通讯作者: Laham, D