arXivDaily arXiv每日学术速递 周一至周五更新
看起来今天可以划水了
arXiv 1908.03067cs.CL
收藏

以关键事实为支点:一个低资源表格到文本生成的两阶段模型

Key Fact as Pivot: A Two-Stage Model for Low Resource Table-to-Text Generation

Peking University(北京大学);Tencent Inc(腾讯公司);Beijing Institute of Big Data Research(北京大数据研究院)

Shuming Ma, Pengcheng Yang, Tianyu Liu, Peng Li, Jie Zhou, Xu Sun

摘要:

表到文本生成的目的是将结构化数据转换为非结构化文本。现有的方法大多采用编码器-解码器框架来学习变换,这需要大规模的训练样本。然而,缺乏大型并行数据是许多领域的主要实际问题。在这项工作中,我们考虑的情况下,低资源表到文本生成,只有有限的并行数据。我们提出了一种新的模型,将生成分为两个阶段:关键事实预测和表面实现。它首先从表中预测关键事实,然后用关键事实生成文本。关键事实预测的训练需要较少的标注数据,而表面实现可以使用伪并行语料库进行训练。我们在传记生成数据集上评估我们的模型。我们的模型可以在只有$1,000$并行数据的情况下获得$27.34$ BLEU评分,而基线模型只能获得$9.71$ BLEU评分的性能。

英文摘要:

Table-to-text generation aims to translate the structured data into the unstructured text. Most existing methods adopt the encoder-decoder framework to learn the transformation, which requires large-scale training samples. However, the lack of large parallel data is a major practical problem for many domains. In this work, we consider the scenario of low resource table-to-text generation, where only limited parallel data is available. We propose a novel model to separate the generation into two stages: key fact prediction and surface realization. It first predicts the key facts from the tables, and then generates the text with the key facts. The training of key fact prediction needs much fewer annotated data, while surface realization can be trained with pseudo parallel corpus. We evaluate our model on a biography generation dataset. Our model can achieve $27.34$ BLEU score with only $1,000$ parallel data, while the baseline model only obtain the performance of $9.71$ BLEU score.

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。

↑