Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models

About

Structured knowledge grounding (SKG) leverages structured knowledge to complete user requests, such as semantic parsing over databases and question answering over knowledge bases. Since the inputs and outputs of SKG tasks are heterogeneous, they have been studied separately by different communities, which limits systematic and compatible research on SKG. In this paper, we overcome this limitation by proposing the UnifiedSKG framework, which unifies 21 SKG tasks into a text-to-text format, aiming to promote systematic SKG research, instead of being exclusive to a single task, domain, or dataset. We use UnifiedSKG to benchmark T5 with different sizes and show that T5, with simple modifications when necessary, achieves state-of-the-art performance on almost all of the 21 tasks. We further demonstrate that multi-task prefix-tuning improves the performance on most tasks, largely improving the overall performance. UnifiedSKG also facilitates the investigation of zero-shot and few-shot learning, and we show that T0, GPT-3, and Codex struggle in zero-shot and few-shot learning for SKG. We also use UnifiedSKG to conduct a series of controlled experiments on structured knowledge encoding variants across SKG tasks. UnifiedSKG is easily extensible to more tasks, and it is open-sourced at https://github.com/hkunlp/unifiedskg.

Tianbao Xie, Chen Henry Wu, Peng Shi, Ruiqi Zhong, Torsten Scholak, Michihiro Yasunaga, Chien-Sheng Wu, Ming Zhong, Pengcheng Yin, Sida I. Wang, Victor Zhong, Bailin Wang, Chengzu Li, Connor Boyle, Ansong Ni, Ziyu Yao, Dragomir Radev, Caiming Xiong, Lingpeng Kong, Rui Zhang, Noah A. Smith, Luke Zettlemoyer, Tao Yu• 2022

Related benchmarks

TaskDatasetResultRank
Knowledge Base Question AnsweringWEBQSP (test)--
143
Text-to-SQLSpider (dev)
EX (All)74.4
100
Text-to-SQLSpider 1.0 (dev)
Exact Match Accuracy71.8
92
Fact VerificationTabFact
Accuracy83.68
73
Table Question AnsweringWikiTQ
Accuracy49.29
65
Knowledge Base Question AnsweringWebQSP Freebase (test)
F1 Score73.9
46
Table Question AnsweringWTQ (test)
Denotation Accuracy49.3
45
Knowledge Base Question AnsweringCWQ (test)
F1 Score68.8
42
Data-to-text generationDART (test)
BLEU46.7
42
Knowledge Base Question AnsweringGrailQA v1.0 (test)--
33
Showing 10 of 40 rows

Other info

Code

Follow for update