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 751800 of 1202 papers

TitleStatusHype
Neural Maximum Subgraph Parsing for Cross-Domain Semantic Dependency AnalysisCode0
Novel positional encodings to enable tree-structured transformers0
Symbolic Priors for RNN-based Semantic ParsingCode0
Knowledge-Aware Conversational Semantic Parsing Over Web Tables0
Policy Shaping and Generalized Update Equations for Semantic Parsing from Denotations0
Sequence-to-Action: End-to-End Semantic Graph Generation for Semantic ParsingCode0
Dependency-based Hybrid Trees for Semantic Parsing0
Neural Compositional Denotational Semantics for Question Answering0
Semantic Role Labeling for Learner Chinese: the Importance of Syntactic Parsing and L2-L1 Parallel DataCode0
Zero-shot Transfer Learning for Semantic Parsing0
Weakly-supervised Neural Semantic Parsing with a Generative Ranker0
Exploiting Rich Syntactic Information for Semantic Parsing with Graph-to-Sequence ModelCode0
The Gap of Semantic Parsing: A Survey on Automatic Math Word Problem Solvers0
Interactive Semantic Parsing for If-Then Recipes via Hierarchical Reinforcement LearningCode0
Question Generation from SQL Queries Improves Neural Semantic Parsing0
Modeling Semantics with Gated Graph Neural Networks for Knowledge Base Question AnsweringCode0
The APVA-TURBO Approach To Question Answering in Knowledge Base0
Natural Language Interface for Databases Using a Dual-Encoder Model0
A Full End-to-End Semantic Role Labeler, Syntactic-agnostic Over Syntactic-aware?0
Frame Semantics across Languages: Towards a Multilingual FrameNet0
Annotation Schemes for Surface Construction Labeling0
Semantic Parsing for Technical Support Questions0
Semi-Supervised Lexicon Learning for Wide-Coverage Semantic Parsing0
Butterfly Effects in Frame Semantic Parsing: impact of data processing on model rankingCode0
Semantic Parsing: Syntactic assurance to target sentence using LSTM Encoder CFG-Decoder0
Robust Text-to-SQL Generation with Execution-Guided DecodingCode0
Memory Augmented Policy Optimization for Program Synthesis and Semantic ParsingCode0
DialSQL: Dialogue Based Structured Query Generation0
Neural Semantic Parsing0
Syntax for Semantic Role Labeling, To Be, Or Not To BeCode0
Biomedical Event Extraction Using Convolutional Neural Networks and Dependency Parsing0
Weakly Supervised Semantic Parsing with Abstract Examples0
Zero-shot Learning of Classifiers from Natural Language Quantification0
Language Generation via DAG Transduction0
German and French Neural Supertagging Experiments for LTAG Parsing0
Active learning for deep semantic parsing0
Discourse Representation Structure ParsingCode0
Accurate SHRG-Based Semantic Parsing0
Learning Cross-lingual Distributed Logical Representations for Semantic Parsing0
Modelling Natural Language, Programs, and their Intersection0
SystemT: Declarative Text Understanding for Enterprise0
GKR: the Graphical Knowledge Representation for semantic parsing0
Graph Algebraic Combinatory Categorial Grammar0
Toward Data-Driven Tutorial Question Answering with Deep Learning Conversational Models0
ALB at SemEval-2018 Task 10: A System for Capturing Discriminative Attributes0
SemEval 2018 Task 6: Parsing Time Normalizations0
SemEval 2019 Shared Task: Cross-lingual Semantic Parsing with UCCA - Call for Participation0
Coarse-to-Fine Decoding for Neural Semantic ParsingCode0
Backpropagating through Structured Argmax using a SPIGOTCode0
Neural Machine Translation for Bilingually Scarce Scenarios: A Deep Multi-task Learning Approach0
Show:102550
← PrevPage 16 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