Semantic Parsing
383 papers with code • 20 benchmarks • 42 datasets
Semantic Parsing is the task of transducing natural language utterances into formal meaning representations. The target meaning representations can be defined according to a wide variety of formalisms. This include linguistically-motivated semantic representations that are designed to capture the meaning of any sentence such as λ-calculus or the abstract meaning representations. Alternatively, for more task-driven approaches to Semantic Parsing, it is common for meaning representations to represent executable programs such as SQL queries, robotic commands, smart phone instructions, and even general-purpose programming languages like Python and Java.
Source: Tranx: A Transition-based Neural Abstract Syntax Parser for Semantic Parsing and Code Generation
Benchmarks
These leaderboards are used to track progress in Semantic Parsing
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Semantic Parsing models and implementationsDatasets
FrameNet
ATIS
WikiSQL
SCAN
Spider-Realistic
WikiTableQuestions
Occluded REID
ComplexWebQuestions
Subtasks
Most implemented papers
NL2Bash: A Corpus and Semantic Parser for Natural Language Interface to the Linux Operating System
TellinaTool/nl2bash
•
•
LREC 2018
We present new data and semantic parsing methods for the problem of mapping English sentences to Bash commands (NL2Bash).
DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs
We introduce a new English reading comprehension benchmark, DROP, which requires Discrete Reasoning Over the content of Paragraphs.
Measuring Compositional Generalization: A Comprehensive Method on Realistic Data
google-research/google-research
•
•
ICLR 2020
We present a large and realistic natural language question answering dataset that is constructed according to this method, and we use it to analyze the compositional generalization ability of three machine learning architectures.
Schema2QA: High-Quality and Low-Cost Q&A Agents for the Structured Web
stanford-oval/genie-toolkit
•
•
The key concept is to cover the space of possible compound queries on the database with a large number of in-domain questions synthesized with the help of a corpus of generic query templates.
AutoQA: From Databases To QA Semantic Parsers With Only Synthetic Training Data
stanford-oval/genie-toolkit
•
•
EMNLP 2020
To demonstrate the generality of AutoQA, we also apply it to the Overnight dataset.
Learning Contextual Representations for Semantic Parsing with Generation-Augmented Pre-Training
Most recently, there has been significant interest in learning contextual representations for various NLP tasks, by leveraging large scale text corpora to train large neural language models with self-supervised learning objectives, such as Masked Language Model (MLM).
PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Models
Large pre-trained language models for textual data have an unconstrained output space; at each decoding step, they can produce any of 10, 000s of sub-word tokens.
Prompt Injection: Parameterization of Fixed Inputs
unbiarirang/prompt-injection
•
•
Through these explorations, we show that PI can be a promising direction for conditioning language models, especially in scenarios with long and fixed prompts.
OpenICL: An Open-Source Framework for In-context Learning
However, the implementation of ICL is sophisticated due to the diverse retrieval and inference methods involved, as well as the varying pre-processing requirements for different models, datasets, and tasks.
A Probabilistic Generative Grammar for Semantic Parsing
The work relies on a novel application of hierarchical Dirichlet processes (HDPs) for structured prediction, which we also present in this manuscript.
