Rows from Many Sources: Enriching row completions from Wikidata with a pre-trained Language Model

TL;DR

This paper enhances row completion in tables by combining knowledge base interpretation with GPT-3 generated text, achieving state-of-the-art results on the WikiTables benchmark.

Contribution

It introduces a novel approach that integrates knowledge base linking with large language model synthesis to improve row augmentation in tables.

Findings

State-of-the-art performance on WikiTables benchmark

Effective synthesis of diverse rows using GPT-3

Improved metadata generation through property linking

Abstract

Row completion is the task of augmenting a given table of text and numbers with additional, relevant rows. The task divides into two steps: subject suggestion, the task of populating the main column; and gap filling, the task of populating the remaining columns. We present state-of-the-art results for subject suggestion and gap filling measured on a standard benchmark (WikiTables). Our idea is to solve this task by harmoniously combining knowledge base table interpretation and free text generation. We interpret the table using the knowledge base to suggest new rows and generate metadata like headers through property linking. To improve candidate diversity, we synthesize additional rows using free text generation via GPT-3, and crucially, we exploit the metadata we interpret to produce better prompts for text generation. Finally, we verify that the additional synthesized content can be linked to the knowledge base or a trusted web source such as Wikipedia.