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

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 201–225 of 1202 papers

Title	Date	Tasks	Status	Score
Holistic Exploration on Universal Decompositional Semantic Parsing: Architecture, Data Augmentation, and LLM Paradigm	Jul 25, 2023	AttributeData Augmentation	CodeCode Available	5
Compositional Generalization with Grounded Language Models	Jun 7, 2024	Knowledge GraphsSemantic Parsing	CodeCode Available	5
A Split-and-Recombine Approach for Follow-up Query Analysis	Sep 19, 2019	Natural Language QueriesSemantic Parsing	CodeCode Available	5
Handling Ontology Gaps in Semantic Parsing	Jun 27, 2024	HallucinationQuestion Answering	CodeCode Available	5
Compositional generalization in semantic parsing with pretrained transformers	Sep 30, 2021	Out-of-Distribution GeneralizationSemantic Parsing	CodeCode Available	5
Compositional Generalization in Semantic Parsing: Pre-training vs. Specialized Architectures	Jul 17, 2020	Language ModelingLanguage Modelling	CodeCode Available	5
A Sketch-Based System for Semantic Parsing	Sep 2, 2019	RerankingSemantic Parsing	CodeCode Available	5
Compositional Task-Oriented Parsing as Abstractive Question Answering	May 4, 2022	abstractive question answeringQuestion Answering	CodeCode Available	5
Greedy, Joint Syntactic-Semantic Parsing with Stack LSTMs	Jun 29, 2016	Semantic Parsing	CodeCode Available	5
Incorporating Lexical and Syntactic Knowledge for Unsupervised Cross-Lingual Transfer	Apr 25, 2024	Cross-Lingual TransferGraph Attention	CodeCode Available	5
TAGPRIME: A Unified Framework for Relational Structure Extraction	May 25, 2022	Event Argument ExtractionLanguage Modelling	CodeCode Available	5
Compositional Generalization and Natural Language Variation: Can a Semantic Parsing Approach Handle Both?	Oct 24, 2020	Semantic Parsing	CodeCode Available	5
Interactive Semantic Parsing for If-Then Recipes via Hierarchical Reinforcement Learning	Aug 21, 2018	Hierarchical Reinforcement Learningreinforcement-learning	CodeCode Available	5
Graphix-T5: Mixing Pre-Trained Transformers with Graph-Aware Layers for Text-to-SQL Parsing	Jan 18, 2023	Domain GeneralizationInductive Bias	CodeCode Available	5
Compositional Generalisation with Structured Reordering and Fertility Layers	Oct 6, 2022	Semantic Parsing	CodeCode Available	5
Learning Language Games through Interaction	Jun 8, 2016	Semantic Parsing	CodeCode Available	5
Merging Weak and Active Supervision for Semantic Parsing	Nov 29, 2019	Active LearningSemantic Parsing	CodeCode Available	5
Complex Question Decomposition for Semantic Parsing	Jul 1, 2019	Semantic Parsing	CodeCode Available	5
Generative Face Completion	Apr 19, 2017	Facial InpaintingSemantic Parsing	CodeCode Available	5
Content Enhanced BERT-based Text-to-SQL Generation	Oct 16, 2019	Code GenerationSemantic Parsing	CodeCode Available	5
Generic Axiomatization of Families of Noncrossing Graphs in Dependency Parsing	Jul 1, 2017	Dependency ParsingSemantic Parsing	CodeCode Available	5
Frustratingly Simple but Surprisingly Strong: Using Language-Independent Features for Zero-shot Cross-lingual Semantic Parsing	Nov 1, 2021	Cross-Lingual TransferPOS	CodeCode Available	5
From Language to Programs: Bridging Reinforcement Learning and Maximum Marginal Likelihood	Apr 25, 2017	reinforcement-learningReinforcement Learning	CodeCode Available	5
Fully-Semantic Parsing and Generation: the BabelNet Meaning Representation	May 1, 2022	Natural Language UnderstandingSemantic Parsing	CodeCode Available	5
A Grammar-Based Structural CNN Decoder for Code Generation	Nov 14, 2018	Code GenerationDecoder	CodeCode Available	5

Show:10 25 50

← PrevPage 9 of 49Next →

All datasets WikiTableQuestions spider CFQ WebQuestionsSP WikiSQL ATIS Geo PTG (czech, MRP 2020)AMR (chinese, MRP 2020)AMR (english, MRP 2020)DRG (english, MRP 2020)DRG (german, MRP 2020)

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	ARTEMIS-DA	Accuracy (Test)	80.8	—	Unverified
2	SynTQA (Oracle)	Test Accuracy	77.5	—	Unverified
3	TabLaP	Accuracy (Test)	76.6	—	Unverified
4	SynTQA (GPT)	Accuracy (Test)	74.4	—	Unverified
5	Mix SC	Accuracy (Test)	73.6	—	Unverified
6	SynTQA (RF)	Accuracy (Test)	71.6	—	Unverified
7	CABINET	Accuracy (Test)	69.1	—	Unverified
8	NormTab+TabSQLify	Accuracy (Test)	68.63	—	Unverified
9	Chain-of-Table	Accuracy (Test)	67.31	—	Unverified
10	Tab-PoT	Accuracy (Test)	66.78	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	RESDSQL-3B + NatSQL	Accuracy	84.1	—	Unverified
2	code-davinci-002 175B (LEVER)	Accuracy	81.9	—	Unverified
3	RASAT+PICARD	Accuracy	75.5	—	Unverified
4	Graphix-3B + PICARD	Accuracy	74	—	Unverified
5	T5-3B + PICARD	Accuracy	71.9	—	Unverified
6	SADGA + GAP	Accuracy	70.1	—	Unverified
7	RATSQL + GAP	Accuracy	69.7	—	Unverified
8	RATSQL + Grammar-Augmented Pre-Training	Accuracy	69.6	—	Unverified
9	RATSQL + BERT	Accuracy	65.6	—	Unverified
10	Exact Set Matching	Accuracy	19.7	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Dynamic Least-to-Most Prompting	Exact Match	95	—	Unverified
2	LeAR	Exact Match	90.9	—	Unverified
3	T5-3B w/ Intermediate Representations	Exact Match	83.8	—	Unverified
4	Hierarchical Poset Decoding	Exact Match	69	—	Unverified
5	Universal Transformer	Exact Match	18.9	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	ReaRev	Accuracy	76.4	—	Unverified
2	NSM+h	Accuracy	74.3	—	Unverified
3	CBR-KBQA	Accuracy	70	—	Unverified
4	STAGG (Yih et al., 2016)	Accuracy	63.9	—	Unverified
5	T5-11B (Raffel et al., 2020)	Accuracy	56.5	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	CABINET	Denotation accuracy (test)	89.5	—	Unverified
2	TAPEX-Large (weak supervision)	Denotation accuracy (test)	89.5	—	Unverified
3	ReasTAP-Large (weak supervision)	Denotation accuracy (test)	89.2	—	Unverified
4	NL2SQL-BERT	Accuracy	89	—	Unverified
5	TAPAS-Large (weak supervision)	Denotation accuracy (test)	83.6	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	PhraseTransformer	Accuracy	90.4	—	Unverified
2	Tranx	Accuracy	86.2	—	Unverified
3	ASN (Rabinovich et al., 2017)	Accuracy	85.3	—	Unverified
4	ZH15 (Zhao and Huang, 2015)	Accuracy	84.2	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	coarse2fine	Accuracy	88.2	—	Unverified
2	PhraseTransformer	Accuracy	87.9	—	Unverified
3	Tranx	Accuracy	87.7	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	PERIN + RobeCzech	F1	92.36	—	Unverified
2	PERIN	F1	92.24	—	Unverified
3	HUJI-KU	F1	58	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	PERIN	F1	80.52	—	Unverified
2	HUJI-KU	F1	45	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	PERIN	F1	80.23	—	Unverified
2	HUJI-KU	F1	52	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	PERIN	F1	94.16	—	Unverified
2	HUJI-KU	F1	63	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	PERIN	F1	89.83	—	Unverified
2	HUJI-KU	F1	62	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	PERIN	F1	92.73	—	Unverified
2	HUJI-KU	F1	80	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	PERIN	F1	89.19	—	Unverified
2	HUJI-KU	F1	54	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	TAPEX-Large	Denotation Accuracy	74.5	—	Unverified
2	TAPAS-Large	Accuracy	67.2	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	PERIN	F1	76.4	—	Unverified
2	HUJI-KU	F1	73	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	PERIN	F1	81.01	—	Unverified
2	HUJI-KU	F1	75	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	HSP	EM	66.18	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	ReasonBERTR	F1 Score	41.3	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	MeMCE	Exact	40.3	—	Unverified