Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userNatural SQL: Making SQL Easier to Infer from Natural Language Specifications
SQL الطبيعية: جعل SQL أسهل للاستنتاج من مواصفات اللغة الطبيعية
322
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
يعد معالجة عدم التطابق بين الأوصاف اللغوية الطبيعية واستعلامات SQL المقابلة تحديا رئيسيا للترجمة النصية إلى SQL. لسد هذه الفجوة، نقترح تمثيل SQL الوسيط (IR) يسمى SQL الطبيعية (Natsql). على وجه التحديد، يحافظ NATSQL على الوظائف الأساسية ل SQL، في حين أنه يبسط الاستفسارات على النحو التالي: (1) الاستغناء عن المشغلين والكلمات الرئيسية مثل المجموعة من قبل المجموعة، بعد، من أجل الانضمام، والتي عادة ما تكون من الصعب العثور على نظرائهم في أوصاف النص؛ (2) إزالة الحاجة إلى السدود المتداخلة وتعيين المشغلين؛ (3) جعل المخطط يربط أسهل عن طريق تقليل العدد المطلوب من عناصر المخطط. على العنكبوت، وهو معيار نصي To-SQL الصعب يحتوي على استفسارات SQL معقدة ومتداخلة، نوضح أن NATSQL تفوق irs غيرها من مصلحة الضرائب الأخرى، وتحسين أداء العديد من نماذج Sota السابقة. علاوة على ذلك، بالنسبة للنماذج الحالية التي لا تدعم جيل SQL القابل للتنفيذ، يمكنك استخدامها NATSQL بسهولة من إنشاء استعلامات SQL القابلة للتنفيذ، وتحقق دقة تنفيذ الحالة الجديدة من بين الفن.
Addressing the mismatch between natural language descriptions and the corresponding SQL queries is a key challenge for text-to-SQL translation. To bridge this gap, we propose an SQL intermediate representation (IR) called Natural SQL (NatSQL). Specifically, NatSQL preserves the core functionalities of SQL, while it simplifies the queries as follows: (1) dispensing with operators and keywords such as GROUP BY, HAVING, FROM, JOIN ON, which are usually hard to find counterparts in the text descriptions; (2) removing the need of nested subqueries and set operators; and (3) making the schema linking easier by reducing the required number of schema items. On Spider, a challenging text-to-SQL benchmark that contains complex and nested SQL queries, we demonstrate that NatSQL outperforms other IRs, and significantly improves the performance of several previous SOTA models. Furthermore, for existing models that do not support executable SQL generation, NatSQL easily enables them to generate executable SQL queries, and achieves the new state-of-the-art execution accuracy.
References used
https://aclanthology.org/
rate research
Read More
Learning to capture text-table alignment is essential for tasks like text-to-SQL. A model needs to correctly recognize natural language references to columns and values and to ground them in the given database schema. In this paper, we present a nove
l weakly supervised Structure-Grounded pretraining framework (STRUG) for text-to-SQL that can effectively learn to capture text-table alignment based on a parallel text-table corpus. We identify a set of novel pretraining tasks: column grounding, value grounding and column-value mapping, and leverage them to pretrain a text-table encoder. Additionally, to evaluate different methods under more realistic text-table alignment settings, we create a new evaluation set Spider-Realistic based on Spider dev set with explicit mentions of column names removed, and adopt eight existing text-to-SQL datasets for cross-database evaluation. STRUG brings significant improvement over BERTLARGE in all settings. Compared with existing pretraining methods such as GRAPPA, STRUG achieves similar performance on Spider, and outperforms all baselines on more realistic sets. All the code and data used in this work will be open-sourced to facilitate future research.
Recent neural text-to-SQL models can effectively translate natural language questions to corresponding SQL queries on unseen databases. Working mostly on the Spider dataset, researchers have proposed increasingly sophisticated solutions to the proble
m. Contrary to this trend, in this paper we focus on simplifications. We begin by building DuoRAT, a re-implementation of the state-of-the-art RAT-SQL model that unlike RAT-SQL is using only relation-aware or vanilla transformers as the building blocks. We perform several ablation experiments using DuoRAT as the baseline model. Our experiments confirm the usefulness of some techniques and point out the redundancy of others, including structural SQL features and features that link the question with the schema.
Strong and affordable in-domain data is a desirable asset when transferring trained semantic parsers to novel domains. As previous methods for semi-automatically constructing such data cannot handle the complexity of realistic SQL queries, we propose
to construct SQL queries via context-dependent sampling, and introduce the concept of topic. Along with our SQL query construction method, we propose a novel pipeline of semi-automatic Text-to-SQL dataset construction that covers the broad space of SQL queries. We show that the created dataset is comparable with expert annotation along multiple dimensions, and is capable of improving domain transfer performance for SOTA semantic parsers.
Counterfactuals are a valuable means for understanding decisions made by ML systems. However, the counterfactuals generated by the methods currently available for natural language text are either unrealistic or introduce imperceptible changes. We pro
pose CounterfactualGAN: a method that combines a conditional GAN and the embeddings of a pretrained BERT encoder to model-agnostically generate realistic natural language text counterfactuals for explaining regression and classification tasks. Experimental results show that our method produces perceptibly distinguishable counterfactuals, while outperforming four baseline methods on fidelity and human judgments of naturalness, across multiple datasets and multiple predictive models.
It is challenging to design profitable and practical trading strategies, as stock price movements are highly stochastic, and the market is heavily influenced by chaotic data across sources like news and social media. Existing NLP approaches largely t
reat stock prediction as a classification or regression problem and are not optimized to make profitable investment decisions. Further, they do not model the temporal dynamics of large volumes of diversely influential text to which the market responds quickly. Building on these shortcomings, we propose a deep reinforcement learning approach that makes time-aware decisions to trade stocks while optimizing profit using textual data. Our method outperforms state-of-the-art in terms of risk-adjusted returns in trading simulations on two benchmarks: Tweets (English) and financial news (Chinese) pertaining to two major indexes and four global stock markets. Through extensive experiments and studies, we build the case for our method as a tool for quantitative trading.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
