MIGA: A Unified Multi-Task Generation Framework for Conversational Text-to-SQL
نویسندگان
چکیده
Conversational text-to-SQL is designed to translate multi-turn natural language questions into their corresponding SQL queries. Most advanced conversational methods are incompatible with generative pre-trained models (PLMs), such as T5. In this paper, we present a two-stage unified MultI-task Generation frAmework (MIGA) that leverages PLMs’ ability tackle text-to-SQL. the pre-training stage, MIGA first decomposes main task several related sub-tasks and then unifies them same sequence-to-sequence (Seq2Seq) paradigm task-specific prompts boost from multi-task training. Later in fine-tuning propose four perturbations alleviate error propagation problem. tends achieve state-of-the-art performance on two benchmarks (SparC CoSQL). We also provide extensive analyses discussions shed light some new perspectives for
منابع مشابه
DeepText: A Unified Framework for Text Proposal Generation and Text Detection in Natural Images
In this paper, we develop a novel unified framework called DeepText for text region proposal generation and text detection in natural images via a fully convolutional neural network (CNN). First, we propose the inception region proposal network (InceptionRPN) and design a set of text characteristic prior bounding boxes to achieve high word recall with only hundred level candidate proposals. Nex...
متن کاملA Unified Implicit Dialog Framework for Conversational Search
We propose a unified Implicit Dialog framework for goaloriented, information seeking tasks of Conversational Search applications. It aims to enable dialog interactions with domain data without replying on explicitly encoded the rules but utilizing the underlying data representation to build the components required for dialog interaction, which we refer as Implicit Dialog in this work. The propo...
متن کاملA General Evaluation Framework for Text Based Conversational Agent
This paper details the development of a new evaluation framework for a text based Conversational Agent (CA). A CA is an intelligent system that handle spoken or/and text based conversations between machine and human. Generally, the lack of evaluation frameworks for CAs effects its development. The idea behind any system’s evaluation is to make sure about the system’s functionalities and to cont...
متن کاملFramework for Abstractive Summarization using Text-to-Text Generation
We propose a new, ambitious framework for abstractive summarization, which aims at selecting the content of a summary not from sentences, but from an abstract representation of the source documents. This abstract representation relies on the concept of Information Items (INIT), which we define as the smallest element of coherent information in a text or a sentence. Our framework differs from pr...
متن کاملA unified framework for multi-level modeling
With the growing importance of modeling in software engineering and knowledge engineering, and the accelerating convergence of these two disciplines through the confluence of internet-based software applications, the need for a simple, unified information modeling framework fulfilling the use cases of both communities has increased significantly over recent years. These use cases include switch...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Proceedings of the ... AAAI Conference on Artificial Intelligence
سال: 2023
ISSN: ['2159-5399', '2374-3468']
DOI: https://doi.org/10.1609/aaai.v37i11.26504