Structure-Aware Pre-Training for Table-to-Text Generation
Year: 2021
Type: article
Abstract: Table-to-text generation is a subtask of datato-text generation which aims to generate naltural language text based on input table.Pretraining techniques have achieved great success on table-to-text generation.However, the pre-trained models used in previous works are typically trained on free-form natural language text while the input of table-to-text task is structured table.In this paper, we propose STTP, a pre-trained model that is trained with tables and their contexts.The STTP model can understand the structured input table and generate fluent text.Experiments on two datasets show the efficacy of our model.
Source: Greater South Information System
DOI: 10.60692/0fdmw-bq218
Authors: Xinyu Xing, Xiaojun Wan
Institution: Peking University
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W6977053591