Web table extraction, retrieval, and augmentation: A survey
Tables are powerful and popular tools for organizing and manipulating data. A vast number
of tables can be found on the Web, which represent a valuable knowledge resource. The …
of tables can be found on the Web, which represent a valuable knowledge resource. The …
Din-sql: Decomposed in-context learning of text-to-sql with self-correction
M Pourreza, D Rafiei - Advances in Neural Information …, 2024 - proceedings.neurips.cc
There is currently a significant gap between the performance of fine-tuned models and
prompting approaches using Large Language Models (LLMs) on the challenging task of text …
prompting approaches using Large Language Models (LLMs) on the challenging task of text …
Question answering in restricted domains: An overview
Automated question answering has been a topic of research and development since the
earliest AI applications. Computing power has increased since the first such systems were …
earliest AI applications. Computing power has increased since the first such systems were …
Rat-sql: Relation-aware schema encoding and linking for text-to-sql parsers
When translating natural language questions into SQL queries to answer questions from a
database, contemporary semantic parsing models struggle to generalize to unseen …
database, contemporary semantic parsing models struggle to generalize to unseen …
A survey on deep learning approaches for text-to-SQL
G Katsogiannis-Meimarakis, G Koutrika - The VLDB Journal, 2023 - Springer
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 …
developed that allow users to pose natural language questions over relational databases …
Spider: A large-scale human-labeled dataset for complex and cross-domain semantic parsing and text-to-sql task
We present Spider, a large-scale, complex and cross-domain semantic parsing and text-to-
SQL dataset annotated by 11 college students. It consists of 10,181 questions and 5,693 …
SQL dataset annotated by 11 college students. It consists of 10,181 questions and 5,693 …
Seq2sql: Generating structured queries from natural language using reinforcement learning
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 …
the ability for users to retrieve facts from a database is limited due to a lack of understanding …
Discovering the syntax and strategies of natural language programming with generative language models
In this paper, we present a natural language code synthesis tool, GenLine, backed by 1) a
large generative language model and 2) a set of task-specific prompts that create or change …
large generative language model and 2) a set of task-specific prompts that create or change …
LGESQL: line graph enhanced text-to-SQL model with mixed local and non-local relations
This work aims to tackle the challenging heterogeneous graph encoding problem in the text-
to-SQL task. Previous methods are typically node-centric and merely utilize different weight …
to-SQL task. Previous methods are typically node-centric and merely utilize different weight …
Language to logical form with neural attention
Semantic parsing aims at mapping natural language to machine interpretable meaning
representations. Traditional approaches rely on high-quality lexicons, manually-built …
representations. Traditional approaches rely on high-quality lexicons, manually-built …