Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userStructure-Grounded Pretraining for Text-to-SQL
هيكل - محاولات محاكاة للنص إلى SQL
291
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
يعد تعلم محاذاة جدول النص أمرا ضروريا للمهام مثل النص إلى SQL. يحتاج النموذج إلى التعرف بشكل صحيح على مراجع اللغة الطبيعية إلى الأعمدة والقيم وإيصارها في مخطط قاعدة البيانات المحدد. في هذه الورقة، نقدم رواية خاضعة للإشراف على أساس إشراف الإشراف على إنشاء هيكل (Stred) للنص إلى SQL والتي يمكن أن تتعلم بفعالية لالتقاط محاذاة جدول النصوص بناء على كوربوس نصي متوازي للنص. نحدد مجموعة من المهام التي تحذر الرواية: تأريض العمود، والتأريض القيمة ورسم الخرائط ذات القيمة العمودية، والاستفادة منهم للتأمر بتشمس الجدول النصي. بالإضافة إلى ذلك، لتقييم الأساليب المختلفة في إطار إعدادات محاذاة النصوص النصية أكثر واقعية، نقوم بإنشاء تقييم جديد تم تعيين العنكبوت على أساس مجموعة ديف العنكبوت مع إزالته الصريحة لأسماء الأعمدة التي تمت إزالتها، واعتماد ثمانية مجموعات بيانات نصية إلى SQL الحالية تقييم قاعدة البيانات. Werug يجلب تحسنا كبيرا على Bertlarge في جميع الإعدادات. بالمقارنة مع طرق الاحتجاج الحالية مثل Grappa، تحقق Strech أداء مماثل على العنكبوت، وتتفوق على جميع خطوط الأساس على مجموعات أكثر واقعية. سيكون جميع التعليمات البرمجية والبيانات المستخدمة في هذا العمل مفتوحة لتسهيل البحث في المستقبل.
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 novel 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.
References used
https://aclanthology.org/
rate research
Read More
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.
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.
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). Specif
ically, 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.
Most available semantic parsing datasets, comprising of pairs of natural utterances and logical forms, were collected solely for the purpose of training and evaluation of natural language understanding systems. As a result, they do not contain any of
the richness and variety of natural-occurring utterances, where humans ask about data they need or are curious about. In this work, we release SEDE, a dataset with 12,023 pairs of utterances and SQL queries collected from real usage on the Stack Exchange website. We show that these pairs contain a variety of real-world challenges which were rarely reflected so far in any other semantic parsing dataset, propose an evaluation metric based on comparison of partial query clauses that is more suitable for real-world queries, and conduct experiments with strong baselines, showing a large gap between the performance on SEDE compared to other common datasets.
This paper describes NAIST's system for the English-to-Japanese Simultaneous Text-to-text Translation Task in IWSLT 2021 Evaluation Campaign. Our primary submission is based on wait-k neural machine translation with sequence-level knowledge distillation to encourage literal translation.
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
