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 451–500 of 1202 papers

TitleStatusHype
Graph-Based Lexicon Expansion with Sparsity-Inducing Penalties—0
Graph-based Semi-Supervised Learning Algorithms for NLP—0
Graph-based Semi-Supervised Model for Joint Chinese Word Segmentation and Part-of-Speech Tagging—0
Graph Enhanced Cross-Domain Text-to-SQL Generation—0
Book Reviews: Ontology-Based Interpretation of Natural Language by Philipp Cimiano, Christina Unger and John McCrae—0
Graph parsing with s-graph grammars—0
DialSQL: Dialogue Based Structured Query Generation—0
BME-UW at SRST-2019: Surface realization with Interpreted Regular Tree Grammars—0
A Comparison of the Events and Relations Across ACE, ERE, TAC-KBP, and FrameNet Annotation Standards—0
ConTFV: A Contrastive Learning Framework for Table-based Fact Verification—0
GRILLBot: An Assistant for Real-World Tasks with Neural Semantic Parsing and Graph-Based Representations—0
Improving Semantic Parsing for Task Oriented Dialog—0
Grounded Semantic Parsing for Complex Knowledge Extraction—0
Grounded Unsupervised Semantic Parsing—0
Improving Text-to-SQL Semantic Parsing with Fine-grained Query Understanding—0
Guided K-best Selection for Semantic Parsing Annotation—0
Unveiling the Black Box of PLMs with Semantic Anchors: Towards Interpretable Neural Semantic Parsing—0
Conversational Semantic Parsing—0
Dialog2API: Task-Oriented Dialogue with API Description and Example Programs—0
Hierarchical Poset Decoding for Compositional Generalization in Language—0
Diagnosing Transformers in Task-Oriented Semantic Parsing—0
BMEAUT at SemEval-2020 Task 2: Lexical Entailment with Semantic Graphs—0
Hinting Semantic Parsing with Statistical Word Sense Disambiguation—0
HLT@SUDA at SemEval 2019 Task 1: UCCA Graph Parsing as Constituent Tree Parsing—0
Copenhagen-Malm\"o: Tree Approximations of Semantic Parsing Problems—0
HopPG: Self-Iterative Program Generation for Multi-Hop Question Answering over Heterogeneous Knowledge—0
How Does Code Pretraining Affect Language Model Task Performance?—0
How Far are We from Effective Context Modeling? An Exploratory Study on Semantic Parsing in Context—0
How well do Computers Solve Math Word Problems? Large-Scale Dataset Construction and Evaluation—0
How Would You Say It? Eliciting Lexically Diverse Dialogue for Supervised Semantic Parsing—0
Huge Automatically Extracted Training-Sets for Multilingual Word SenseDisambiguation—0
HUJI-KU at MRP~2020: Two Transition-based Neural Parsers—0
DEXTER: Deep Encoding of External Knowledge for Named Entity Recognition in Virtual Assistants—0
Development of a General-Purpose Categorial Grammar Treebank—0
Human Semantic Parsing for Person Re-identification—0
HuRIC: a Human Robot Interaction Corpus—0
Hybrid Question Answering over Knowledge Base and Free Text—0
Hyperedge Replacement and Nonprojective Dependency Structures—0
ICT:A System Combination for Chinese Semantic Dependency Parsing—0
Identifying Pathological Findings in German Radiology Reports Using a Syntacto-semantic Parsing Approach—0
Identifying Various Kinds of Event Mentions in K-Parser Output—0
Biphasic Face Photo-Sketch Synthesis via Semantic-Driven Generative Adversarial Network with Graph Representation Learning—0
IHS-RD-Belarus at SemEval-2016 Task 9: Transition-based Chinese Semantic Dependency Parsing with Online Reordering and Bootstrapping.—0
Imitation learning for structured prediction in natural language processing—0
An Instance Level Approach for Shallow Semantic Parsing in Scientific Procedural Text—0
ImPaKT: A Dataset for Open-Schema Knowledge Base Construction—0
Improved Semantic Parsers For If-Then Statements—0
Developing Production-Level Conversational Interfaces with Shallow Semantic Parsing—0
A Unified Framework for Discourse Argument Identification via Shallow Semantic Parsing—0
Deterministic natural language generation from meaning representations for machine translation—0
Show:102550
← PrevPage 10 of 25Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ARTEMIS-DAAccuracy (Test)80.8—Unverified
2SynTQA (Oracle)Test Accuracy77.5—Unverified
3TabLaPAccuracy (Test)76.6—Unverified
4SynTQA (GPT)Accuracy (Test)74.4—Unverified
5Mix SCAccuracy (Test)73.6—Unverified
6SynTQA (RF)Accuracy (Test)71.6—Unverified
7CABINETAccuracy (Test)69.1—Unverified
8NormTab+TabSQLifyAccuracy (Test)68.63—Unverified
9Chain-of-TableAccuracy (Test)67.31—Unverified
10Tab-PoTAccuracy (Test)66.78—Unverified
#ModelMetricClaimedVerifiedStatus
1RESDSQL-3B + NatSQLAccuracy84.1—Unverified
2code-davinci-002 175B (LEVER)Accuracy81.9—Unverified
3RASAT+PICARDAccuracy75.5—Unverified
4Graphix-3B + PICARDAccuracy74—Unverified
5T5-3B + PICARDAccuracy71.9—Unverified
6SADGA + GAPAccuracy70.1—Unverified
7RATSQL + GAPAccuracy69.7—Unverified
8RATSQL + Grammar-Augmented Pre-TrainingAccuracy69.6—Unverified
9RATSQL + BERTAccuracy65.6—Unverified
10Exact Set MatchingAccuracy19.7—Unverified
#ModelMetricClaimedVerifiedStatus
1Dynamic Least-to-Most PromptingExact Match95—Unverified
2LeARExact Match90.9—Unverified
3T5-3B w/ Intermediate RepresentationsExact Match83.8—Unverified
4Hierarchical Poset DecodingExact Match69—Unverified
5Universal TransformerExact Match18.9—Unverified
#ModelMetricClaimedVerifiedStatus
1ReaRevAccuracy76.4—Unverified
2NSM+hAccuracy74.3—Unverified
3CBR-KBQAAccuracy70—Unverified
4STAGG (Yih et al., 2016)Accuracy63.9—Unverified
5T5-11B (Raffel et al., 2020)Accuracy56.5—Unverified
#ModelMetricClaimedVerifiedStatus
1CABINETDenotation accuracy (test)89.5—Unverified
2TAPEX-Large (weak supervision)Denotation accuracy (test)89.5—Unverified
3ReasTAP-Large (weak supervision)Denotation accuracy (test)89.2—Unverified
4NL2SQL-BERTAccuracy89—Unverified
5TAPAS-Large (weak supervision)Denotation accuracy (test)83.6—Unverified
#ModelMetricClaimedVerifiedStatus
1PhraseTransformerAccuracy90.4—Unverified
2TranxAccuracy86.2—Unverified
3ASN (Rabinovich et al., 2017)Accuracy85.3—Unverified
4ZH15 (Zhao and Huang, 2015)Accuracy84.2—Unverified
#ModelMetricClaimedVerifiedStatus
1coarse2fineAccuracy88.2—Unverified
2PhraseTransformerAccuracy87.9—Unverified
3TranxAccuracy87.7—Unverified
#ModelMetricClaimedVerifiedStatus
1PERIN + RobeCzechF192.36—Unverified
2PERINF192.24—Unverified
3HUJI-KUF158—Unverified
#ModelMetricClaimedVerifiedStatus
1PERINF180.52—Unverified
2HUJI-KUF145—Unverified
#ModelMetricClaimedVerifiedStatus
1PERINF180.23—Unverified
2HUJI-KUF152—Unverified
#ModelMetricClaimedVerifiedStatus
1PERINF194.16—Unverified
2HUJI-KUF163—Unverified
#ModelMetricClaimedVerifiedStatus
1PERINF189.83—Unverified
2HUJI-KUF162—Unverified
#ModelMetricClaimedVerifiedStatus
1PERINF192.73—Unverified
2HUJI-KUF180—Unverified
#ModelMetricClaimedVerifiedStatus
1PERINF189.19—Unverified
2HUJI-KUF154—Unverified
#ModelMetricClaimedVerifiedStatus
1TAPEX-LargeDenotation Accuracy74.5—Unverified
2TAPAS-LargeAccuracy67.2—Unverified
#ModelMetricClaimedVerifiedStatus
1PERINF176.4—Unverified
2HUJI-KUF173—Unverified
#ModelMetricClaimedVerifiedStatus
1PERINF181.01—Unverified
2HUJI-KUF175—Unverified
#ModelMetricClaimedVerifiedStatus
1HSPEM66.18—Unverified
#ModelMetricClaimedVerifiedStatus
1ReasonBERTRF1 Score41.3—Unverified
#ModelMetricClaimedVerifiedStatus
1MeMCEExact40.3—Unverified