SOTAVerified

Semantic Parsing

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

Papers

Showing 51100 of 1202 papers

TitleStatusHype
LAGr: Label Aligned Graphs for Better Systematic Generalization in Semantic ParsingCode1
LAGr: Labeling Aligned Graphs for Improving Systematic Generalization in Semantic ParsingCode1
Large Language Models are Versatile Decomposers: Decompose Evidence and Questions for Table-based ReasoningCode1
Learning Contextual Representations for Semantic Parsing with Generation-Augmented Pre-TrainingCode1
Contextual Semantic Parsing for Multilingual Task-Oriented DialoguesCode1
AMR Parsing as Sequence-to-Graph TransductionCode1
Leveraging Semantic Parsing for Relation Linking over Knowledge BasesCode1
LEVER: Learning to Verify Language-to-Code Generation with ExecutionCode1
COGS: A Compositional Generalization Challenge Based on Semantic InterpretationCode1
Modern Baselines for SPARQL Semantic ParsingCode1
Neural Machine Translation for Query Construction and CompositionCode1
NL2Bash: A Corpus and Semantic Parser for Natural Language Interface to the Linux Operating SystemCode1
Code Generation from Natural Language with Less Prior Knowledge and More Monolingual DataCode1
Fine-tuned LLMs Know More, Hallucinate Less with Few-Shot Sequence-to-Sequence Semantic Parsing over WikidataCode1
Conversational Question Answering over Knowledge Graphs with Transformer and Graph Attention NetworksCode1
Calibrated Interpretation: Confidence Estimation in Semantic ParsingCode1
CABINET: Content Relevance based Noise Reduction for Table Question AnsweringCode1
Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLsCode1
Break It Down: A Question Understanding BenchmarkCode1
Bridging Textual and Tabular Data for Cross-Domain Text-to-SQL Semantic ParsingCode1
Benchmarking Meaning Representations in Neural Semantic ParsingCode1
Cityscapes-Panoptic-Parts and PASCAL-Panoptic-Parts datasets for Scene UnderstandingCode1
Code-Style In-Context Learning for Knowledge-Based Question AnsweringCode1
CogIE: An Information Extraction Toolkit for Bridging Texts and CogNetCode1
An Investigation of LLMs' Inefficacy in Understanding Converse RelationsCode1
Complex Knowledge Base Question Answering: A SurveyCode1
Compositional Semantic Parsing on Semi-Structured TablesCode1
Constrained Language Models Yield Few-Shot Semantic ParsersCode1
A Comprehensive Exploration on WikiSQL with Table-Aware Word ContextualizationCode1
CST5: Data Augmentation for Code-Switched Semantic ParsingCode1
BenchCLAMP: A Benchmark for Evaluating Language Models on Syntactic and Semantic ParsingCode1
DeepA2: A Modular Framework for Deep Argument Analysis with Pretrained Neural Text2Text Language ModelsCode1
Diverse Demonstrations Improve In-context Compositional GeneralizationCode1
A Survey on Non-Autoregressive Generation for Neural Machine Translation and BeyondCode1
A Pilot Study of Text-to-SQL Semantic Parsing for VietnameseCode1
Dynamic Hybrid Relation Network for Cross-Domain Context-Dependent Semantic ParsingCode1
3D-to-2D Distillation for Indoor Scene ParsingCode1
Exploring Neural Methods for Parsing Discourse Representation StructuresCode1
FeTaQA: Free-form Table Question AnsweringCode1
ArcaneQA: Dynamic Program Induction and Contextualized Encoding for Knowledge Base Question AnsweringCode1
Frame-Semantic Parsing with Softmax-Margin Segmental RNNs and a Syntactic ScaffoldCode1
Generating Data for Symbolic Language with Large Language ModelsCode1
A Graph-Based Neural Model for End-to-End Frame Semantic ParsingCode1
GraphQ IR: Unifying the Semantic Parsing of Graph Query Languages with One Intermediate RepresentationCode1
AIT-QA: Question Answering Dataset over Complex Tables in the Airline IndustryCode1
Identity-Guided Human Semantic Parsing for Person Re-IdentificationCode1
Abstract Meaning Representation Guided Graph Encoding and Decoding for Joint Information ExtractionCode1
Improving Compositional Generalization in Semantic ParsingCode1
Improving Multi-hop Knowledge Base Question Answering by Learning Intermediate Supervision SignalsCode1
AutoQA: From Databases To QA Semantic Parsers With Only Synthetic Training DataCode1
Show:102550
← PrevPage 2 of 25Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ARTEMIS-DAAccuracy (Test)80.8Unverified
2SynTQA (Oracle)Test Accuracy77.5Unverified
3TabLaPAccuracy (Test)76.6Unverified
4SynTQA (GPT)Accuracy (Test)74.4Unverified
5Mix SCAccuracy (Test)73.6Unverified
6SynTQA (RF)Accuracy (Test)71.6Unverified
7CABINETAccuracy (Test)69.1Unverified
8NormTab+TabSQLifyAccuracy (Test)68.63Unverified
9Chain-of-TableAccuracy (Test)67.31Unverified
10Tab-PoTAccuracy (Test)66.78Unverified
#ModelMetricClaimedVerifiedStatus
1RESDSQL-3B + NatSQLAccuracy84.1Unverified
2code-davinci-002 175B (LEVER)Accuracy81.9Unverified
3RASAT+PICARDAccuracy75.5Unverified
4Graphix-3B + PICARDAccuracy74Unverified
5T5-3B + PICARDAccuracy71.9Unverified
6SADGA + GAPAccuracy70.1Unverified
7RATSQL + GAPAccuracy69.7Unverified
8RATSQL + Grammar-Augmented Pre-TrainingAccuracy69.6Unverified
9RATSQL + BERTAccuracy65.6Unverified
10Exact Set MatchingAccuracy19.7Unverified
#ModelMetricClaimedVerifiedStatus
1Dynamic Least-to-Most PromptingExact Match95Unverified
2LeARExact Match90.9Unverified
3T5-3B w/ Intermediate RepresentationsExact Match83.8Unverified
4Hierarchical Poset DecodingExact Match69Unverified
5Universal TransformerExact Match18.9Unverified
#ModelMetricClaimedVerifiedStatus
1ReaRevAccuracy76.4Unverified
2NSM+hAccuracy74.3Unverified
3CBR-KBQAAccuracy70Unverified
4STAGG (Yih et al., 2016)Accuracy63.9Unverified
5T5-11B (Raffel et al., 2020)Accuracy56.5Unverified
#ModelMetricClaimedVerifiedStatus
1CABINETDenotation accuracy (test)89.5Unverified
2TAPEX-Large (weak supervision)Denotation accuracy (test)89.5Unverified
3ReasTAP-Large (weak supervision)Denotation accuracy (test)89.2Unverified
4NL2SQL-BERTAccuracy89Unverified
5TAPAS-Large (weak supervision)Denotation accuracy (test)83.6Unverified
#ModelMetricClaimedVerifiedStatus
1PhraseTransformerAccuracy90.4Unverified
2TranxAccuracy86.2Unverified
3ASN (Rabinovich et al., 2017)Accuracy85.3Unverified
4ZH15 (Zhao and Huang, 2015)Accuracy84.2Unverified
#ModelMetricClaimedVerifiedStatus
1coarse2fineAccuracy88.2Unverified
2PhraseTransformerAccuracy87.9Unverified
3TranxAccuracy87.7Unverified
#ModelMetricClaimedVerifiedStatus
1PERIN + RobeCzechF192.36Unverified
2PERINF192.24Unverified
3HUJI-KUF158Unverified
#ModelMetricClaimedVerifiedStatus
1PERINF180.52Unverified
2HUJI-KUF145Unverified
#ModelMetricClaimedVerifiedStatus
1PERINF180.23Unverified
2HUJI-KUF152Unverified
#ModelMetricClaimedVerifiedStatus
1PERINF194.16Unverified
2HUJI-KUF163Unverified
#ModelMetricClaimedVerifiedStatus
1PERINF189.83Unverified
2HUJI-KUF162Unverified
#ModelMetricClaimedVerifiedStatus
1PERINF192.73Unverified
2HUJI-KUF180Unverified
#ModelMetricClaimedVerifiedStatus
1PERINF189.19Unverified
2HUJI-KUF154Unverified
#ModelMetricClaimedVerifiedStatus
1TAPEX-LargeDenotation Accuracy74.5Unverified
2TAPAS-LargeAccuracy67.2Unverified
#ModelMetricClaimedVerifiedStatus
1PERINF176.4Unverified
2HUJI-KUF173Unverified
#ModelMetricClaimedVerifiedStatus
1PERINF181.01Unverified
2HUJI-KUF175Unverified
#ModelMetricClaimedVerifiedStatus
1HSPEM66.18Unverified
#ModelMetricClaimedVerifiedStatus
1ReasonBERTRF1 Score41.3Unverified
#ModelMetricClaimedVerifiedStatus
1MeMCEExact40.3Unverified