论文标题
MIGA：统一的多任务生成框架，用于对话文本到SQL
MIGA: A Unified Multi-task Generation Framework for Conversational Text-to-SQL
论文作者
论文摘要
对话文本到SQL旨在将多转弯自然语言问题转化为相应的SQL查询。大多数最先进的对话文本-SQL方法与生成的预训练的语言模型（PLM）（例如T5）不相容。在本文中，我们提出了一个两阶段的统一多任务生成框架（MIGA），该框架利用PLMS来处理对话性文本到SQL的能力。在训练前阶段，MIGA首先将主要任务分解为几个相关的子任务，然后将它们统一为相同的顺序到序列（SEQ2SEQ）范式，并使用特定于任务的自然语言提示从多任务训练中提高主要任务。在微调阶段的后期，我们提出了四个SQL扰动来减轻错误传播问题。 MIGA倾向于在两个基准（SPARC和CoSQL）上实现最先进的性能。我们还提供了广泛的分析和讨论，以阐明一些新观点的对话文本到SQL。
Conversational text-to-SQL is designed to translate multi-turn natural language questions into their corresponding SQL queries. Most state-of-the-art conversational text- to-SQL methods are incompatible with generative pre-trained language models (PLMs), such as T5. In this paper, we present a two-stage unified MultI-task Generation frAmework (MIGA) that leverages PLMs' ability to tackle conversational text-to-SQL. In the pre-training stage, MIGA first decomposes the main task into several related sub-tasks and then unifies them into the same sequence-to-sequence (Seq2Seq) paradigm with task-specific natural language prompts to boost the main task from multi-task training. Later in the fine-tuning stage, we propose four SQL perturbations to alleviate the error propagation problem. MIGA tends to achieve state-of-the-art performance on two benchmarks (SparC and CoSQL). We also provide extensive analyses and discussions to shed light on some new perspectives for conversational text-to-SQL.
