TaBERT: Pretraining for joint understanding of textual and tabular data
Recent years have witnessed the burgeoning of pretrained language models (LMs) for text-
based natural language (NL) understanding tasks. Such models are typically trained on free …
based natural language (NL) understanding tasks. Such models are typically trained on free …
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 …
Introduction to neural network‐based question answering over knowledge graphs
N Chakraborty, D Lukovnikov… - … : Data Mining and …, 2021 - Wiley Online Library
Question answering has emerged as an intuitive way of querying structured data sources
and has attracted significant advancements over the years. A large body of recent work on …
and has attracted significant advancements over the years. A large body of recent work on …
A comprehensive exploration on wikisql with table-aware word contextualization
We present SQLova, the first Natural-language-to-SQL (NL2SQL) model to achieve human
performance in WikiSQL dataset. We revisit and discuss diverse popular methods in …
performance in WikiSQL dataset. We revisit and discuss diverse popular methods in …
Compositional generalization in semantic parsing: Pre-training vs. specialized architectures
While mainstream machine learning methods are known to have limited ability to
compositionally generalize, new architectures and techniques continue to be proposed to …
compositionally generalize, new architectures and techniques continue to be proposed to …
Semantic evaluation for text-to-SQL with distilled test suites
We propose test suite accuracy to approximate semantic accuracy for Text-to-SQL models.
Our method distills a small test suite of databases that achieves high code coverage for the …
Our method distills a small test suite of databases that achieves high code coverage for the …
A review of nlidb with deep learning: findings, challenges and open issues
Relational databases are storage for a massive amount of data. Knowledge of structured
query language is a prior requirement to access that data. That is not possible for all non …
query language is a prior requirement to access that data. That is not possible for all non …
Grappa: Grammar-augmented pre-training for table semantic parsing
We present GraPPa, an effective pre-training approach for table semantic parsing that learns
a compositional inductive bias in the joint representations of textual and tabular data. We …
a compositional inductive bias in the joint representations of textual and tabular data. We …
Ryansql: Recursively applying sketch-based slot fillings for complex text-to-sql in cross-domain databases
DH Choi, MC Shin, EG Kim, DR Shin - Computational Linguistics, 2021 - direct.mit.edu
Text-to-SQL is the problem of converting a user question into an SQL query, when the
question and database are given. In this article, we present a neural network approach …
question and database are given. In this article, we present a neural network approach …
LI-EMRSQL: Linking information enhanced Text2SQL parsing on complex electronic medical records
Converting natural language text into executable SQL queries significantly impacts the
healthcare domain, specifically when applied to electronic medical records. Given that …
healthcare domain, specifically when applied to electronic medical records. Given that …