Towards Controlled Table-to-Text Generation with Scientific Reasoning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Guo, Zhixin, Zhou, Jianping, Qi, Jiexing, Yan, Mingxuan, He, Ziwei, Zheng, Guanjie, Lin, Zhouhan, Wang, Xinbing, Zhou, Chenghu
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914730025680896
author Guo, Zhixin
Zhou, Jianping
Qi, Jiexing
Yan, Mingxuan
He, Ziwei
Zheng, Guanjie
Lin, Zhouhan
Wang, Xinbing
Zhou, Chenghu
author_facet Guo, Zhixin
Zhou, Jianping
Qi, Jiexing
Yan, Mingxuan
He, Ziwei
Zheng, Guanjie
Lin, Zhouhan
Wang, Xinbing
Zhou, Chenghu
contents The sheer volume of scientific experimental results and complex technical statements, often presented in tabular formats, presents a formidable barrier to individuals acquiring preferred information. The realms of scientific reasoning and content generation that adhere to user preferences encounter distinct challenges. In this work, we present a new task for generating fluent and logical descriptions that match user preferences over scientific tabular data, aiming to automate scientific document analysis. To facilitate research in this direction, we construct a new challenging dataset CTRLSciTab consisting of table-description pairs extracted from the scientific literature, with highlighted cells and corresponding domain-specific knowledge base. We evaluated popular pre-trained language models to establish a baseline and proposed a novel architecture outperforming competing approaches. The results showed that large models struggle to produce accurate content that aligns with user preferences. As the first of its kind, our work should motivate further research in scientific domains.
format Preprint
id arxiv_https___arxiv_org_abs_2312_05402
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Towards Controlled Table-to-Text Generation with Scientific Reasoning
Guo, Zhixin
Zhou, Jianping
Qi, Jiexing
Yan, Mingxuan
He, Ziwei
Zheng, Guanjie
Lin, Zhouhan
Wang, Xinbing
Zhou, Chenghu
Computation and Language
The sheer volume of scientific experimental results and complex technical statements, often presented in tabular formats, presents a formidable barrier to individuals acquiring preferred information. The realms of scientific reasoning and content generation that adhere to user preferences encounter distinct challenges. In this work, we present a new task for generating fluent and logical descriptions that match user preferences over scientific tabular data, aiming to automate scientific document analysis. To facilitate research in this direction, we construct a new challenging dataset CTRLSciTab consisting of table-description pairs extracted from the scientific literature, with highlighted cells and corresponding domain-specific knowledge base. We evaluated popular pre-trained language models to establish a baseline and proposed a novel architecture outperforming competing approaches. The results showed that large models struggle to produce accurate content that aligns with user preferences. As the first of its kind, our work should motivate further research in scientific domains.
title Towards Controlled Table-to-Text Generation with Scientific Reasoning
topic Computation and Language
url https://arxiv.org/abs/2312.05402