Triple-to-Text: Converting RDF Triples into High-Quality Natural Languages via Optimizing an Inverse KL Divergence

By Yaoming Zhu, Juncheng Wan, Zhiming Zhou, Liheng Chen, Lin Qiu, Weinan Zhang, Xin Jiang, Yong Yu. 2019

30 citations recorded by the source corpus.

Knowledge base is one of the main forms to represent information in a structured way. A knowledge base typically consists of Resource Description Frameworks (RDF) triples which describe the entities and their relations. Generating natural language description of the knowledge base is an important task in NLP, which has been formulated as a conditional language generation task and tackled using the sequence-to-sequence framework. Current works mostly train the language models by maximum likelihood estimation, which tends to generate lousy sentences. In this paper, we argue that such a problem of maximum likelihood estimation is intrinsic, which is generally irrevocable via changing network structures. Accordingly, we propose a novel Triple-to-Text (T2T) framework, which approximately optimizes the inverse Kullback-Leibler (KL) divergence between the distributions of the real and generated sentences. Due to the nature that inverse KL imposes large penalty on fake-looking samples, the proposed method can significantly reduce the probability of generating low-quality sentences. Our experiments on three real-world datasets demonstrate that T2T can generate higher-quality sentences and outperform baseline models in several evaluation metrics.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Natural Language Processing, Natural Language Generation

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Natural Language Processing

In Natural Language Generation

Citations in the corpus

DART: Open-Domain Structured Data Record to Text Generation (2020, background): “…2018; Gehrmann et al., 2018; Puduppully et al., 2018, 2019; Iso et al., 2019; Castro Ferreira et al., 2019; Shen et al., 2019; Roberti et al., 2019; Zhu et al., 2019b; Koncel-Kedziorski et al., 2019; Ye et al., 2020; Harkous et al., 2020; Wang et al., 2020b; Song et al., 2020; Shahidi et al.,…”
ESPRIT: Explaining Solutions to Physical Reasoning Tasks (2020, background): “, 2018; Perez-Beltrachini and Lapata, 2018), descriptions of knowledge bases (ODonnell et al., 2000; Trisedya et al., 2018; Zhu et al., 2019; Yu et al., 2019) and source code (Iyer et al.”
Denoising Pre-Training and Data Augmentation Strategies for Enhanced RDF Verbalization with Transformers (2020, unknown): “-decoder framework showed promising results, with some limitations on unseen domains. Following WebNLG2017, multiple works were conducted to cope with the witnessed drawbacks of participants’ system. Zhu et al. (2019) argued that Kullback-Leibler (KL) divergence should be avoided. Minimizing the KL ”