arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1910.08435cs.CL
收藏

使用局部知识图谱构造将Seq2Seq模型扩展到多文档输入

Using Local Knowledge Graph Construction to Scale Seq2Seq Models to Multi-Document Inputs

FAIR(Facebook人工智能研究院);LORIA(洛林计算机科学及其应用研究实验室);CNRS(法国国家科学研究中心)

Angela Fan, Claire Gardent, Chloe Braud, Antoine Bordes

摘要:

基于查询的开放域NLP任务需要从长而多样的Web结果中进行信息合成。当前的方法使用诸如TF-IDF排名的方法提取web文本的部分作为序列到序列模型的输入。我们建议为每个查询构建一个局部图结构的知识库,从而压缩网络搜索信息并减少冗余。我们表明,通过将图线性化为结构化的输入序列,模型可以在标准的序列到序列设置中对图表示进行编码。对于两个生成任务,非常长的文本输入,长形式的问答和多文档摘要,饲料图形表示作为输入可以实现更好的性能比使用检索的文本部分。

英文摘要:

Query-based open-domain NLP tasks require information synthesis from long and diverse web results. Current approaches extractively select portions of web text as input to Sequence-to-Sequence models using methods such as TF-IDF ranking. We propose constructing a local graph structured knowledge base for each query, which compresses the web search information and reduces redundancy. We show that by linearizing the graph into a structured input sequence, models can encode the graph representations within a standard Sequence-to-Sequence setting. For two generative tasks with very long text input, long-form question answering and multi-document summarization, feeding graph representations as input can achieve better performance than using retrieved text portions.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑