UnifiedSKG：用文本到文本语言模型统一和多任务结构化知识Grounding
UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models
摘要：
结构化知识基础（SKG）利用结构化知识来完成用户请求，例如数据库上的语义解析和知识库上的问答。由于SKG任务的输入和输出是异构的，它们被不同的群体分开研究，这限制了对SKG的系统性和兼容性研究。在本文中，我们通过提出UnifiedSKG框架来克服这一限制，该框架将21个SKG任务统一为文本到文本格式，旨在促进系统的SKG研究，而不是仅限于单个任务，领域或数据集。我们使用UnifiedSKG对不同尺寸的T5进行基准测试，结果表明，T5在必要时进行简单修改后，几乎在所有21项任务上都实现了最先进的性能。我们进一步证明了多任务前缀调优提高了大多数任务的性能，大大提高了整体性能。UnifiedSKG还促进了对zero-shot和few-shot学习的研究，我们表明T0，GPT-3和Codex在SKG的zero-shot和少样本学习中挣扎。我们还使用UnifiedSKG对SKG任务中的结构化知识编码变体进行了一系列对照实验。UnifiedSKG可轻松扩展到更多任务，并且在https://github.com/hkunlp/unifiedskg上开源。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
