首页|集成显著性话语上下文窗口采样方法的长对话摘要生成模型

集成显著性话语上下文窗口采样方法的长对话摘要生成模型

扫码查看
针对对话语料的特点,提出一种集成显著性话语上下文窗口采样方法的长对话摘要生成模型.该模型分为两个模块:1)显著性话语上下文窗口采样模块将对话话语进行显著性评估,以显著性话语作为采样锚点,然后设置采样窗口,将采样锚点左右相邻的话语一起提取为片段,提取出来的片段包含更丰富的话语关系;2)片段间信息融合摘要生成模块利用 Transformer 块,将相互独立的片段进行信息融合,加强片段之间的语义关系,并且为片段在生成摘要期间分配混合权重.利用一致性损失机制,鼓励显著性话语上下文窗口采样模块确定更佳的采样锚点.在基于查询的长对话摘要公开数据集 QMSum 上的实验结果表明,该模型在ROUGE 评估指标上的分数高于现有最好的模型.
A Long Dialogue Summary Model Integrating Salience Discourse Context Window Sampling Methods
A long dialogue summary generation model with integrated salience discourse context window sampling method(SDCWS)is proposed according to the characteristics of dialogue corpus.The model is divided into two modules.1)The salience discourse context window sampling module(CWS)evaluates the dialogue discourse for salience,uses the salient discourse as the sampling anchor point,and then sets the sampling window to extract the discourse adjacent to the left and right of the sampling anchor point together as fragments,containing richer discourse relations.2)The inter-fragment information fusion summary generation module(IF)uses the transformer block to fuse information from mutually independent fragments,enhancing the semantic relationships between fragments and assigning blended weights to fragments during summary generation.The loss-of-consistency mechanism is used to encourage the salience discourse context window sampling module to determine better sampling anchors.Experimental results on the publicly available query-based long conversation summary dataset QMSum show that scores of the proposed model are significantly higher than the best existing model on the ROUGE evaluation metric.

long dialogue summarywindow samplingsalient discourseinformation fusiongenerating models

吴杰、王鹏鸣、熊正坤

展开 >

华东交通大学信息工程学院, 南昌 330013

温州理工学院数据科学与人工智能学院, 温州 325035

长对话摘要 窗口采样 显著性话语 信息融合 生成模型

国家自然科学基金国家自然科学基金江西省重点研发计划

621660186226601720203BBE53029

2024

北京大学学报(自然科学版)
北京大学

北京大学学报(自然科学版)

CSTPCD北大核心
影响因子:0.785
ISSN:0479-8023
年,卷(期):2024.60(1)
  • 21