Semantic Parsing
195 papers with code • 17 benchmarks • 32 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
| Trend | Dataset | Best Model | Paper Title | Paper | Code | Compare |
|---|---|---|---|---|---|---|
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
Datasets
FrameNet
ATIS
WikiSQL
SCAN
NomBank
SPIDER
WikiTableQuestions
ComplexWebQuestions
Occluded REID
AMR Bank
Subtasks
Greatest papers with code
TAPAS: Weakly Supervised Table Parsing via Pre-training
huggingface/transformers
•
•
ACL 2020
In this paper, we present TAPAS, an approach to question answering over tables without generating logical forms.
Ranked #1 on
Semantic Parsing
on SQA
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
huggingface/transformers
•
•
arXiv 2019
Transfer learning, where a model is first pre-trained on a data-rich task before being fine-tuned on a downstream task, has emerged as a powerful technique in natural language processing (NLP).
Ranked #1 on
Question Answering
on BoolQ
Learning to Generalize from Sparse and Underspecified Rewards
google-research/google-research
•
•
The parameters of the auxiliary reward function are optimized with respect to the validation performance of a trained policy.
Non-Autoregressive Semantic Parsing for Compositional Task-Oriented Dialog
facebookresearch/pytext
•
•
NAACL 2021
Semantic parsing using sequence-to-sequence models allows parsing of deeper representations compared to traditional word tagging based models.
SPARQL query generation for complex question answering with BERT and BiLSTM-based model
In this paper we describe question answering system for answering of complex questions over Wikidata knowledge base.
N-LTP: A Open-source Neural Chinese Language Technology Platform with Pretrained Models
HIT-SCIR/ltp
•
•
In addition, knowledge distillation where the single-task model teaches the multi-task model is further introduced to encourage the multi-task model to surpass its single-task teacher.
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
charlesq34/pointnet
•
•
CVPR 2017
Point cloud is an important type of geometric data structure.
Ranked #2 on
Scene Segmentation
on ScanNet
The Natural Language Decathlon: Multitask Learning as Question Answering
salesforce/decaNLP
•
•
ICLR 2019
Though designed for decaNLP, MQAN also achieves state of the art results on the WikiSQL semantic parsing task in the single-task setting.
SLING: A framework for frame semantic parsing
We describe SLING, a framework for parsing natural language into semantic frames.
RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parsers
PaddlePaddle/PaddleNLP
•
•
ACL 2020
The generalization challenge lies in (a) encoding the database relations in an accessible way for the semantic parser, and (b) modeling alignment between database columns and their mentions in a given query.
Ranked #3 on
Semantic Parsing
on spider
