Two-layer mutually reinforced random walk for improved multi-party meeting summarization
Two-layer mutually reinforced random walk for improved multi-party meeting summarization
复制标题
DOI：
10.1109/slt.2012.6424268
复制
发表时间：
2012-12
期刊：
影响因子：
--
通讯作者：
Yun-Nung (Vivian) Chen;Florian Metze
中科院分区：
文献类型：
--
作者：
Yun-Nung (Vivian) Chen;Florian Metze
本文提出了一种改进的多方会话自动摘要方法，该方法构造了一个包含话语间、说话人间和说话人间关系的两层图。每个话语和每个说话人分别表示为图的话语层和说话人层中的节点，并且两个节点之间的边通过两个话语、两个说话人或话语和说话人之间的相似性来加权。话语之间的关系是通过词汇相似度通过词重叠或主题相似度通过概率潜在语义分析（PLSA）。通过图中的层内和层间传播，来自不同层的分数可以相互加强，使得话语可以自动地与来自相同说话者的话语和类似话语共享分数。对于ASR输出和手动成绩单，实验证实了在两层图中涉及说话人信息用于摘要的功效。
This paper proposes an improved approach of summarization for spoken multi-party interaction, in which a two-layer graph with utterance-to-utterance, speaker-to-speaker, and speaker-to-utterance relations is constructed. Each utterance and each speaker are represented as a node in the utterance-layer and speaker-layer of the graph respectively, and the edge between two nodes is weighted by the similarity between the two utterances, the two speakers, or the utterance and the speaker. The relation between utterances is evaluated by lexical similarity via word overlap or topical similarity via probabilistic latent semantic analysis (PLSA). By within- and between-layer propagation in the graph, the scores from different layers can be mutually reinforced so that utterances can automatically share the scores with the utterances from the same speaker and similar utterances. For both ASR output and manual transcripts, experiments confirmed the efficacy of involving speaker information in the two-layer graph for summarization.