Operations Guided Neural Networks for High Fidelity Data-To-Text Generation
This addresses a critical issue for domains like sports reporting that require high-fidelity text generation from structured data, though it is incremental as it builds on existing encoder-decoder methods.
The paper tackled the problem of neural data-to-text generation often producing descriptions inconsistent with input structured data, especially in domains requiring inference or calculations, by proposing the OpAtt framework that utilizes pre-executed symbolic operations, resulting in clear improvements in fidelity on two sports datasets.
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.