This paper studies multi-turn text-to-sql generation, which is a new but important task in semantic parsing. In order to deal with its two challenges, i.e., multi-turn interaction and cross-domain evaluation, this pap...
详细信息
This paper studies multi-turn text-to-sql generation, which is a new but important task in semantic parsing. In order to deal with its two challenges, i.e., multi-turn interaction and cross-domain evaluation, this paper proposes a multiple-integration encoder, which derives the vector representations of user utterances and database schemas using three custom-designed modules for information integration. First, an utterance representation enhancing module is built to integrate the information of history utterances into the representation of each token in current utterance by attentive selection. Second, a schema discrepancy enhancing module is designed to integrate previous predicted sql query into the representation of schema items. Third, a latent schema linking module is employed to integrate schema information into utterance representations for better dealing with unseen database schemas. These three modules are all implemented based on a lightweight multi-head attention mechanism, which reduces the number of parameters in conventional multi-head attention. Experimental results on the SParC dataset show that our method achieved better accuracy of multi-turn text-to-sql generation than the most advanced benchmarks. Further ablations studies and analysis also demonstrate the effectiveness of the three modules designed for information integration in the encoder.
To bridge the gap between users and data, numerous text-to-sql systems have been developed that allow users to pose natural language questions over relational databases. Recently, novel text-to-sql systems are adoptin...
详细信息
To bridge the gap between users and data, numerous text-to-sql systems have been developed that allow users to pose natural language questions over relational databases. Recently, novel text-to-sql systems are adopting deep learning methods with very promising results. At the same time, several challenges remain open making this area an active and flourishing field of research and development. To make real progress in building text-to-sql systems, we need to de-mystify what has been done, understand how and when each approach can be used, and, finally, identify the research challenges ahead of us. The purpose of this survey is to present a detailed taxonomy of neural text-to-sql systems that will enable a deeper study of all the parts of such a system. This taxonomy will allow us to make a better comparison between different approaches, as well as highlight specific challenges in each step of the process, thus enabling researchers to better strategise their quest towards the "holy grail" of database accessibility.
The challenge of natural language processing is from natural language to logical form (sql). In this article, we present an fuzzy semantic to structured query language (F-Semtosql) neural approach that is a fuzzy deci...
详细信息
The challenge of natural language processing is from natural language to logical form (sql). In this article, we present an fuzzy semantic to structured query language (F-Semtosql) neural approach that is a fuzzy decision semantic deep network query model based on demand aggregation. It aims to address the problem of the complex and cross-domain text-to-sql generation task. The corpus is trained as the input word vector of the model with LSTM and Word2Vec embedding technology. Combined with the dependency graph method, the problem of sql statement generation is converted to slot filling. Complex tasks are divided into four levels via F-Semtosql and constructed by the need of aggregation. At the same time, to avoid the order problem in the traditional model effectively, we have adopted the attention mechanism and used a fuzzy decision mechanism to improve the model decision. On the challenging text-to-sql benchmark Spider and the other three datasets, F-Semtosql achieves faster convergence and occupies the first position.
Software analytics integrated with complex databases can deliver project intelligence into the hands of software engineering (SE) experts for satisfying their information needs. A new and promising machine learning te...
详细信息
Software analytics integrated with complex databases can deliver project intelligence into the hands of software engineering (SE) experts for satisfying their information needs. A new and promising machine learning technique known as text-to-sql automatically extracts information for users of complex databases without the need to fully understand the database structure nor the accompanying query language. Users pose their request as so-called natural language utterance, i.e., question. Our goal was evaluating the performance and applicability of text-to-sql approaches on data derived from tools typically used in the workflow of software engineers for satisfying their information needs. We carefully selected and discussed five seminal as well as state-of-the-art text-to-sql approaches and conducted a comparative assessment using the large-scale, cross-domain Spider dataset and the SE domain-specific SEOSS-Queries dataset. Furthermore, we study via a survey how SE professionals perform in satisfying their information needs and how they perceive text-to-sql approaches. For the best performing approach, we observe a high accuracy of 94% in query prediction when training specifically on SE data. This accuracy is almost independent of the query's complexity. At the same time, we observe that SE professionals have substantial deficits in satisfying their information needs directly via sql queries. Furthermore, SE professionals are open for utilizing text-to-sql approaches in their daily work, considering them less time-consuming and helpful. We conclude that state-of-the-art text-to-sql approaches are applicable in SE practice for day-to-day information needs.
Recently, the text-to-sql task has received much attention. Many sophisticated neural models have been invented that achieve significant results. Most current work assumes that all the inputs are legal and the model s...
详细信息
Recently, the text-to-sql task has received much attention. Many sophisticated neural models have been invented that achieve significant results. Most current work assumes that all the inputs are legal and the model should generate an sql query for any input. However, in the real scenario, users are allowed to enter the arbitrary text that may not be answered by an sql query. In this article, we focus on the issue-answerability classification for the text-to-sql system, which aims to distinguish the answerability of the question according to the given database schema. Existing methods concatenate the question and the database schema into a sentence, then fine-tune the pre-trained language model on the answerability classification task. In this way, the database schema is regarded as sequence text that may ignore the intrinsic structure relationship of the schema data, and the attention that represents the correlation between the question token and the database schema items is not well designed. To this end, we propose a relational Question-Schema graph framework that can effectively model the attention and relation between question and schema. In addition, a conditional layer normalization mechanism is employed to modulate the pre-trained language model to generate better question representation. Experiments demonstrate that the proposed framework outperforms all existing models by largemargins, achieving new state of the art on the benchmark TRIAGEsql. Specifically, the model attains 88.41%, 78.24%, and 75.98% in Precision, Recall, and F1, respectively. Additionally, it outperforms the baseline by approximately 4.05% in Precision, 6.96% in Recall, and 6.01% in F1.
text-to-sql emerges to play an important role in interactive data analysis, which provides a friendly interface for converting natural language into relational database language (i.e., sql). In order to translate a us...
详细信息
text-to-sql emerges to play an important role in interactive data analysis, which provides a friendly interface for converting natural language into relational database language (i.e., sql). In order to translate a user's query into an executable sql statement, semantic parsing is essential to the transformation process. In particular, existing efforts provide some feasible solutions, and state-of-the-art models mainly adopt the sketch-based paradigm such that template values are to be filled. To this end, most methods extract values based on column representations. However, if the query contains multiple values that belong to different columns, these methods may fail to extract the values accurately. Moreover, it can be difficult to infer the right values when the query does not explicitly mention the corresponding column names. To bridge the gap, we propose a novel neural architecture, namely, ER-sql for learning enhanced representations for text-to-sql. Based on pre-trained model BERT, ER-sql uses column contents to better extract features of columns. Moreover, ER-sql harnesses the column representations to latently reformulate the query. To verify the effectiveness of ER-sql, comprehensive experiments demonstrate that ER-sql achieves better results than existing models on the benchmark dataset Wikisql, as well as on a representative Chinese dataset TableQA. (C) 2021 The Author(s). Published by Elsevier B.V.
text-to-sql aims at translating textual questions into the corresponding sql *** tables are widely created for high-frequent *** text-to-sql has emerged as an important task,recent studies paid little attention to the...
详细信息
text-to-sql aims at translating textual questions into the corresponding sql *** tables are widely created for high-frequent *** text-to-sql has emerged as an important task,recent studies paid little attention to the task over aggregate *** increased aggregate tables bring two challenges:(1)mapping of natural language questions and relational databases will suffer from more ambiguity,(2)modern models usually adopt self-attention mechanism to encode database schema and *** mechanism is of quadratic time complexity,which will make inferring more time-consuming as input sequence length *** this paper,we introduce a novel approach named WAGG for text-to-sql over aggregate *** effectively select among ambiguous items,we propose a relation selection mechanism for relation *** deal with high computation costs,we introduce a dynamical pruning strategy to discard unrelated items that are common for aggregate *** also construct a new large-scale dataset SpiderwAGG extended from Spider dataset for validation,where extensive experiments show the effectiveness and efficiency of our proposed method with 4%increase of accuracy and 15%decrease of inference time w.r.t a strong baseline RAT-sql.
text-to-sql task maps natural language utterances to structured queries that can be issued to a database. State-of-theart (SOTA) systems rely on finetuning large, pre-trained language models in conjunction with constr...
详细信息
ISBN:
(纸本)9798350396904
text-to-sql task maps natural language utterances to structured queries that can be issued to a database. State-of-theart (SOTA) systems rely on finetuning large, pre-trained language models in conjunction with constrained decoding applying a sql parser. On the well established Spider dataset, we begin with Oracle studies: specifically, choosing an Oracle hypothesis from a SOTA model's 10-best list, yields a 7:7% absolute improvement in both exact match (EM) and execution (EX) accuracy, showing significant potential improvements with reranking. Identifying coherence and correctness as reranking approaches, we design a model generating a query plan and propose a heuristic schema linking algorithm. Combining both approaches, with T5-Large, we obtain a consistent 1% improvement in EM accuracy, and a 2:5% improvement in EX, establishing a new SOTA for this task. Our comprehensive error studies on DEV data show the underlying difficulty in making progress on this task.
Sophisticated text-to-sql methods often face errors, such as schema-linking errors, join errors, nested errors, and group-by errors. To mitigate these, it's crucial to filter out unnecessary tables and columns, fo...
详细信息
ISBN:
(纸本)9783031683084;9783031683091
Sophisticated text-to-sql methods often face errors, such as schema-linking errors, join errors, nested errors, and group-by errors. To mitigate these, it's crucial to filter out unnecessary tables and columns, focusing the language model on relevant ones. Previous methods have attempted to sort tables and columns based on relevance or directly identify necessary elements, but these approaches suffer from long training times, high costs with GPT-4 tokens, or poor schema linking performance. We propose a two-step schema linking method: first, generate an initial sql query using the full database schema;then, extract the relevant tables and columns to form a concise schema. This method, tested with Code Llama and GPT-4, shows optimal performance compared to mainstream methods on the Spider dataset, reducing errors and improving efficiency in sql generation.
text-to-sql parsing has attracted substantial attention recently due to its potential to remove barriers for non-expert end users interacting with databases. A key challenge in text-to-sql parsing is developing effect...
详细信息
ISBN:
(纸本)9798400704314
text-to-sql parsing has attracted substantial attention recently due to its potential to remove barriers for non-expert end users interacting with databases. A key challenge in text-to-sql parsing is developing effective encoding mechanisms to capture the complex relationships between question words, database schemas, and their associated connections within the heterogeneous graph structure. Existing approaches typically introduce some useful multi-hop structures manually and then incorporate them into graph neural networks (GNNs) by stacking multiple layers, which (1) ignore the difficult-to-identify but meaningful semantics embedded in the multi-hop reasoning path, and (2) are limited by the expressive capability of GNN to capture long-range dependencies among the heterogeneous graph. To address these shortcomings, we introduce GRL-sql, a graph reasoning enhanced language model, which innovatively applies structure encoding to capture the dependencies between node pairs, encompassing one-hop, multi-hop and distance information, subsequently enriched through self-attention for enhanced representational power over GNNs. Furthermore, GRL-sql incorporates an interaction module that enables joint reasoning and fusion over the question-schema representations for enhancing global context modeling. Comprehensive experiments demonstrate the effectiveness and robustness of our proposed GRL-sql.
暂无评论