Logic-Consistency Text Generation from Semantic Parses

By Chang Shu, Yusen Zhang, Xiangyu Dong, Peng Shi, Tao Yu, Rui Zhang. 2021

38 citations recorded by the source corpus.

Text generation from semantic parses is to generate textual descriptions for formal representation inputs such as logic forms and SQL queries. This is challenging due to two reasons: (1) the complex and intensive inner logic with the data scarcity constraint, (2) the lack of automatic evaluation metrics for logic consistency. To address these two challenges, this paper first proposes SNOWBALL, a framework for logic consistent text generation from semantic parses that employs an iterative training procedure by recursively augmenting the training set with quality control. Second, we propose a novel automatic metric, BLEC, for evaluating the logical consistency between the semantic parses and generated texts. The experimental results on two benchmark datasets, Logic2Text and Spider, demonstrate the SNOWBALL framework enhances the logic consistency on both BLEC and human evaluation. Furthermore, our statistical analysis reveals that BLEC is more logically consistent with human evaluation than general-purpose automatic metrics including BLEU, ROUGE and, BLEURT. Our data and code are available at https://github.com/Ciaranshu/relogic.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Information Extraction, 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 Information Extraction

In Natural Language Generation

Citations in the corpus

UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models (2022, background): “For high-ﬁdelity NLG, we report BLEC (Shu et al., 2021), which is the exact match between keywords in the formal language and the natural language.”