arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2001.03897cs.CLcs.LG
收藏

利用依赖信息的随机自然语言生成

Stochastic Natural Language Generation Using Dependency Information

Sharif University of Technology(谢里夫理工大学)

Elham Seifossadat, Hossein Sameti

摘要:

提出了一种基于随机语料库的自然语言文本生成模型。我们的模型首先通过一个特征集对训练数据中的依赖关系进行编码,然后将这些特征连接起来,为给定的含义表示生成一个新的依赖树,最后从生成的依赖树生成一个自然语言话语。我们测试我们的模型在九个领域从表格,对话行为和RDF格式。我们的模型优于在表格数据集上训练的基于语料库的最先进方法,并且还实现了与基于神经网络的方法相当的结果,这些方法在对话行为,E2E和WebNLG数据集上训练,用于BLEU和ERR评估指标。此外,通过报告人的评价结果,我们表明,我们的模型产生高质量的话语方面的信息量和自然性以及质量。

英文摘要:

This article presents a stochastic corpus-based model for generating natural language text. Our model first encodes dependency relations from training data through a feature set, then concatenates these features to produce a new dependency tree for a given meaning representation, and finally generates a natural language utterance from the produced dependency tree. We test our model on nine domains from tabular, dialogue act and RDF format. Our model outperforms the corpus-based state-of-the-art methods trained on tabular datasets and also achieves comparable results with neural network-based approaches trained on dialogue act, E2E and WebNLG datasets for BLEU and ERR evaluation metrics. Also, by reporting Human Evaluation results, we show that our model produces high-quality utterances in aspects of informativeness and naturalness as well as quality.

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。

↑