Natural language is hypothetically the best user interface for many domains. However, general models that provide an interface between natural language and any other domain still do not exist. Providing natural language interface to relational databases could possibly attract a vast majority of users that are or are not proficient with query languages. With the rise of deep learning techniques, there is extensive ongoing research in designing a suitable natural language interface to relational databases.
This survey aims to overview some of the latest methods and models proposed in the area of SQL query generation from natural language. We describe models with various architectures such as convolutional neural networks, recurrent neural networks, pointer networks, reinforcement learning, etc. Several datasets intended to address the problem of SQL query generation are interpreted and briefly overviewed. In the end, evaluation metrics utilized in the field are presented mainly as a combination of execution accuracy and logical form accuracy.
With the future striving toward data-centric decision-making, seamless access to databases is of utmost importance. There is extensive research on creating an efficient text-to-sql (TEXT2SQL) model to access data from the database. Using a Natural language is one of the best interfaces that can bridge the gap between the data and results by accessing the database efficiently, especially for non-technical users. It will open the doors and create tremendous interest among users who are well versed in technical skills or not very skilled in query languages. Even if numerous deep learning-based al…
A significant amount of the world's knowledge is stored in relational databases. However, the ability for users to retrieve facts from a database is limited due to a lack of understanding of query languages such as SQL. We propose Seq2SQL, a deep neural network for translating natural language questions to corresponding SQL queries. Our model leverages the structure of SQL queries to significantly reduce the output space of generated queries. Moreover, we use rewards from in-the-loop query execution over the database to learn a policy to generate unordered parts of the query, which we show are…
To access data stored in relational databases, users need to understand the database schema and write a query using a query language such as SQL. To simplify this task, text-to-SQL models attempt to translate a user's natural language question to corresponding SQL query. Recently, several generative text-to-SQL models have been developed. We propose a novel discriminative re-ranker to improve the performance of generative text-to-SQL models by extracting the best SQL query from the beam output predicted by the text-to-SQL generator, resulting in improved performance in the cases where the best…
Ping An Life Insurance Company of China, Ltd（中国平安人寿保险股份有限公司）
On the WikiSQL benchmark, state-of-the-art text-to-SQL systems typically take a slot-filling approach by building several dedicated models for each type of slots. Such modularized systems are not only complex butalso of limited capacity for capturing inter-dependencies among SQL clauses. To solve these problems, this paper proposes a novel extraction-linking approach, where a unified extractor recognizes all types of slot mentions appearing in the question sentence before a linker maps the recognized columns to the table schema to generate executable SQL queries. Trained with automatically gen…
Tencent AI Lab（腾讯人工智能实验室）；IBM Research（IBM研究院）；Peking University（北京大学）
Previous work approaches the SQL-to-text generation task using vanilla Seq2Seq models, which may not fully capture the inherent graph-structured information in SQL query. In this paper, we first introduce a strategy to represent the SQL query as a directed graph and then employ a graph-to-sequence model to encode the global structure information into node embeddings. This model can effectively learn the correlation between the SQL query pattern and its interpretation. Experimental results on the WikiSQL dataset and Stackoverflow dataset show that our model significantly outperforms the Seq2Seq…
The Hong Kong University of Science and Technology（香港科技大学）；AI Group, WeBank Co., Ltd（微众银行人工智能部）
Speech-based inputs have been gaining significant momentum with the popularity of smartphones and tablets in our daily lives, since voice is the most easiest and efficient way for human-computer interaction. This paper works towards designing more effective speech-based interfaces to query the structured data in relational databases. We first identify a new task named Speech-to-SQL, which aims to understand the information conveyed by human speech and directly translate it into structured query language (SQL) statements. A naive solution to this problem can work in a cascaded manner, that is, …
Relational databases are among the most widely used architectures to store massive amounts of data in the modern world. However, there is a barrier between these databases and the average user. The user often lacks the knowledge of a query language such as SQL required to interact with the database. The NL2SQL task aims at finding deep learning approaches to solve this problem by converting natural language questions into valid SQL queries. Given the sensitive nature of some databases and the growing need for data privacy, we have presented an approach with data privacy at its core. We have pa…
IIT Guwahati（印度理工学院古瓦哈提分校）；IBM Information Management, India Software Lab（IBM信息管理印度软件实验室）
This paper concerns with the conversion of a Spoken English Language Query into SQL for retrieving data from RDBMS. A User submits a query as speech signal through the user interface and gets the result of the query in the text format. We have developed the acoustic and language models using which a speech utterance can be converted into English text query and thus natural language processing techniques can be applied on this English text query to generate an equivalent SQL query. For conversion of speech into English text HTK and Julius tools have been used and for conversion of English text …
Most recent research on Text-to-SQL semantic parsing relies on either parser itself or simple heuristic based approach to understand natural language query (NLQ). When synthesizing a SQL query, there is no explicit semantic information of NLQ available to the parser which leads to undesirable generalization performance. In addition, without lexical-level fine-grained query understanding, linking between query and database can only rely on fuzzy string match which leads to suboptimal performance in real applications. In view of this, in this paper we present a general-purpose, modular neural se…
Yale University（耶鲁大学）；Salesforce Research（赛富时研究院）；University of Michigan（密歇根大学）；Cornell University（康奈尔大学）
We present CoSQL, a corpus for building cross-domain, general-purpose database (DB) querying dialogue systems. It consists of 30k+ turns plus 10k+ annotated SQL queries, obtained from a Wizard-of-Oz (WOZ) collection of 3k dialogues querying 200 complex DBs spanning 138 domains. Each dialogue simulates a real-world DB query scenario with a crowd worker as a user exploring the DB and a SQL expert retrieving answers with SQL, clarifying ambiguous questions, or otherwise informing of unanswerable questions. When user questions are answerable by SQL, the expert describes the SQL and execution resul…
Electronic medical records (EMR) contain comprehensive patient information and are typically stored in a relational database with multiple tables. Effective and efficient patient information retrieval from EMR data is a challenging task for medical experts. Question-to-SQL generation methods tackle this problem by first predicting the SQL query for a given question about a database, and then, executing the query on the database. However, most of the existing approaches have not been adapted to the healthcare domain due to a lack of healthcare Question-to-SQL dataset for learning models specifi…
We focus on the cross-domain context-dependent text-to-SQL generation task. Based on the observation that adjacent natural language questions are often linguistically dependent and their corresponding SQL queries tend to overlap, we utilize the interaction history by editing the previous predicted query to improve the generation quality. Our editing mechanism views SQL as sequences and reuses generation results at the token level in a simple manner. It is flexible to change individual tokens and robust to error propagation. Furthermore, to deal with complex table structures in different domain…
Cornell University（康奈尔大学）；Stanford University（斯坦福大学）；Microsoft Research（微软研究院）；Microsoft Business Application Group（微软商业应用集团）
We present a sequence-to-action parsing approach for the natural language to SQL task that incrementally fills the slots of a SQL query with feasible actions from a pre-defined inventory. To account for the fact that typically there are multiple correct SQL queries with the same or very similar semantics, we draw inspiration from syntactic parsing techniques and propose to train our sequence-to-action models with non-deterministic oracles. We evaluate our models on the WikiSQL dataset and achieve an execution accuracy of 83.7% on the test set, a 2.1% absolute improvement over the models traine…
Xi’an Jiaotong University（西安交通大学）；Beijing University of Posts and Telecommunications（北京邮电大学）；Microsoft Research Asia（微软亚洲研究院）
We present a neural approach called IRNet for complex and cross-domain Text-to-SQL. IRNet aims to address two challenges: 1) the mismatch between intents expressed in natural language (NL) and the implementation details in SQL; 2) the challenge in predicting columns caused by the large number of out-of-domain words. Instead of end-to-end synthesizing a SQL query, IRNet decomposes the synthesis process into three phases. In the first phase, IRNet performs a schema linking over a question and a database schema. Then, IRNet adopts a grammar-based neural model to synthesize a SemQL query which is …
Query Carefully: Detecting the Unanswerables in Text-to-SQL Tasks
Institute of Computer Science, Zurich University of Applied Sciences（计算机科学研究所，应用科学大学苏黎世）；Institute of Medical Virology, University of Zurich（医学病毒学研究所，苏黎世大学）；Department of Gastroenterology and Hepatology, University Hospital Zurich, University of Zurich（消化内科与肝病科，苏黎世大学医院，苏黎世大学）
Recently, context-dependent text-to-SQL semantic parsing which translates natural language into SQL in an interaction process has attracted a lot of attention. Previous works leverage context-dependence information either from interaction history utterances or the previous predicted SQL queries but fail in taking advantage of both since of the mismatch between natural language and logic-form SQL. In this work, we propose a History Information Enhanced text-to-SQL model (HIE-SQL) to exploit context-dependence information from both history utterances and the last predicted SQL query. In view of …
Pi-SQL: Enhancing Text-to-SQL with Fine-Grained Guidance from Pivot Programming Languages
Shanghai University of Finance and Economics（上海金融学院）；Tsinghua University（清华大学）；Beihang University（北航）；Wuhan University（武汉大学）；Southern University of Science and Technology（南方科技大学）
Cooperative SQL Generation for Segmented Databases By Using Multi-functional LLM Agents
School of Computer Science, Northwestern Polytechnical University（西北工业大学计算机学院）；Big Data Shortage and Management, MIIT（工业和信息化部大数据短缺与管理局）；School of Computing, National University of Singapore（新加坡国立大学计算机学院）；School of Computing and Information Systems, Singapore Management University（新加坡管理大学计算与信息系统学院）
