paper-with-me

Papers

Using Database Rule for Weak Supervised Text-to-SQL Generation

2019-07-01 · Tong Guo, Huilin Gao

We present a simple way to do the task of text-to-SQL problem with weak supervision. We call it Rule-SQL. Given the question and the answer from the database table without the SQL logic form, Rule-SQL use the rules based on table column names and question string for the SQL exploration first and then use the explored SQL for supervised training. We design several rules for reducing the exploration search space. For the deep model, we leverage BERT for the representation layer and separate the model to SELECT, AGG and WHERE parts. The experiment result on WikiSQL outperforms the strong baseline of full supervision and is comparable to the start-of-the-art weak supervised mothods.

📄 PDF Abstract BibTeX arXiv:1907.00620

Code (2)

guotong1988/Rule-SQL 공식 구현 pytorch
guotong1988/weak-supervised-Rule-Text2SQL pytorch

Tasks

Text to SQLText-To-SQL

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Residual Connection 설명 없음
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.
Weight Decay 설명 없음
Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Adam 설명 없음

Similar Papers 제목 키워드 기반

RulePrompt: Weakly Supervised Text Classification with Prompting PLMs and Self-Iterative Logical Rules

2024-03-05 · Miaomiao Li, Jiaqi Zhu, Yang Wang, Yi Yang 외

Weakly supervised text classification (WSTC), also called zero-shot or dataless text classification, has attracted increasing attention due to its applicability in classifying a mass of texts within the dynamic and open …

Pseudo Labeltext-classificationText Classification

Denoising Multi-Source Weak Supervision for Neural Text Classification

2020-10-09 · Findings of the Association for Computational Linguistics 2020 · Wendi Ren, Yinghao Li, Hanting Su, David Kartchner 외

We study the problem of learning neural text classifiers without using any labeled data, but only easy-to-provide rules as multiple weak supervision sources. This problem is challenging because rule-induced weak labels a…

ClassificationDenoisingGeneral Classificationtext-classification+1

ReGAL: Rule-Generative Active Learning for Model-in-the-Loop Weak Supervision

2020-10-16 · NeurIPS Workshop HAMLETS 2020 12 · Anonymous

One of the main bottlenecks to extending deep learning systems to new domains is the prohibitive cost of acquiring sufficient training labels. While many previous works have sought to alleviate this problem with weak su…

Active Learningtext-classificationText Classification

Adaptive Rule Discovery for Labeling Text Data

2020-05-13 · Sainyam Galhotra, Behzad Golshan, Wang-Chiew Tan

Creating and collecting labeled data is one of the major bottlenecks in machine learning pipelines and the emergence of automated feature generation techniques such as deep learning, which typically requires a lot of tra…

SeqGenSQL -- A Robust Sequence Generation Model for Structured Query Language

2020-11-07 · Ning li, Bethany Keller, Mark Butler, Daniel Cer

We explore using T5 (Raffel et al. (2019)) to directly translate natural language questions into SQL statements. General purpose natural language that interfaces to information stored within databases requires flexibly t…

Text GenerationText to SQLText-To-SQL