Operations Guided Neural Networks For High Fidelity Data-to-text Generation | Awesome LLM Papers Add your paper to Awesome LLM Papers

Operations Guided Neural Networks For High Fidelity Data-to-text Generation

Feng Nie, Jinpeng Wang, Jin-Ge Yao, Rong Pan, Chin-Yew Lin . Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing 2018 – 52 citations

[Paper]   Search on Google Scholar   Search on Semantic Scholar
Content Enrichment Datasets EMNLP Efficiency Interdisciplinary Approaches Neural Machine Translation RAG Tools Training Techniques Variational Autoencoders

Recent neural models for data-to-text generation are mostly based on data-driven end-to-end training over encoder-decoder networks. Even though the generated texts are mostly fluent and informative, they often generate descriptions that are not consistent with the input structured data. This is a critical issue especially in domains that require inference or calculations over raw data. In this paper, we attempt to improve the fidelity of neural data-to-text generation by utilizing pre-executed symbolic operations. We propose a framework called Operation-guided Attention-based sequence-to-sequence network (OpAtt), with a specifically designed gating mechanism as well as a quantization module for operation results to utilize information from pre-executed operations. Experiments on two sports datasets show our proposed method clearly improves the fidelity of the generated texts to the input structured data.

Similar Work