TableLlama: Towards Open Large Generalist Models for Tables
arXiv
TableLlama
supLLama 2
independent
none
TURL Dataset
MIT
Wikidata
2023
Li
Table-GPT: Table-tuned GPT for Diverse Table Tasks
arXiv
Table-GPT
supGPT-3.5
independent
none
TURL Dataset
NotSpecified
Efthymiou, Limaye, Sherlock, T2D
2022
Abdelmageed
JenTab: Do CTA solutions affect the entire scores?
KGC
JenTab
unsupfeatures
independent
none
SemTab2020
Apache 2.0
CSV
DBpedia,Wikidata
CEA,CTA,CPA
2022
Chen
LinkingPark: An automatic semantic table interpretation system
JOWS
LinkingPark
unsupfeatures
independent
none
SemTab2021
MIT
CSV
DBpedia,Wikidata - ElasticSearch
CEA,CTA,CPA
2022
Cremaschi
s-elBat: a Semantic Interpretation Approach for Messy taBle-s
SemTab
s-Elbat
unsupfeatures
independent
none
Semtab2022
Apache 2.0
CSV,JSON
DBpedia,Wikidata - Lamapi
CEA,CTA,CPA
2022
Deng
TURL: Table Understanding through Representation Learning
SIGMOD
TURL
supBERT
independent
none
T2D, WikiGS
Apache 2.0
web tables
Freebase, Wikidata, DBpedia
CTA,CPA,CEA
2022
Gottschalk
Tab2KG: Semantic table interpretation with lightweight semantic profiles
SWJ
Tab2KG
supSiamese network
independent
none
Datasets on github, subsets of DBpedia and schema.org
MIT
CSV
DBpedia, Schema.org
Data graph which represents the content of the table (TURTLE)
2022
Huynh
From Heuristics to Language Models: A Journey Through the Universe of Semantic Table Interpretation with DAGOBAH
SemTab
DAGOBAH SL2022
hybridHeuristics + Transformer-based embeddings
independent
Fully-automated
semtab 2022
Orange
CSV
DBpedia,Wikidata, Schema.org - ElasticSearch
CTA,CPA,CEA
2022
Liu
Radar Station: Using KG Embeddings for Semantic Table Interpretation and Entity Disambiguation
ISWC
Radar Station
hybridHeuristics + KG Embedding
independent
none
T2D, Limaye, Tough Tables, ShortTables
Orange
CSV, TXT, XLSX
Wikidata
2022
Suhara
Annotating Columns with Pre-trained Language Models
SIGMOD
Doduo
supBERT
independent
none
WikiTable, VizNet
Apache 2.0
Freebase,DBpedia
2021
Abdelmageed
JenTab Meets SemTab 2021’s New Challenges
SemTab
JenTab
unsupfeatures
independent
none
SemTab2021
Apache 2.0
CSV
DBpedia,Wikidata
CEA,CTA,CPA
2021
Abdelmageed
JenTab: A Toolkit for Semantic Table Annotations
KGC
JenTab
unsupfeatures
independent
none
SemTab2020
Apache 2.0
CSV
DBpedia,Wikidata
CEA,CTA,CPA
2021
Avogadro
MantisTable V: a novel and efficient approach to Semantic Table Interpretation
SemTab
MantisTable V
unsupfeatures
independent
none
Semtab2021
Apache 2.0
DBpedia,Wikidata - Lamapi
CEA,CTA,CPA
2021
Baazouzi
Kepler-aSI at SemTab 2021
SemTab
KEPLER-ASI
unsupfeatures
independent
none
Semtab2021
NotSpecified
CSV
Wikidata
CEA,CTA,CPA
2021
Heist
Information Extraction From Co-Occurring Similar Entities
WWW
CaLiGraph extraction framework
hybriddistant supervision + rule mining
independent
none
GPL 3.0
web tables
CaliGraph,DBpedia,Yago
RDF assertions
2021
Huynh
DAGOBAH: Table and Graph Contexts for Efficient Semantic Annotation of Tabular Data
SemTab
DAGOBAH SL 2021
hybridfeatures + embeddings, Matching
independent
Fully-automated
SemTab2021
Orange
CSV, TXT, XLSX
DBpedia,Wikidata - ElasticSearch
JSON
2021
Nguyen
SemTab 2021: Tabular Data Annotation with MTab Tool
SemTab
MTab
unsupfeatures
independent
Fully-automated
SemTab2021
MIT
CSV
DBpedia,Wikidata - Custom BM25
CEA,CTA,CPA
2021
Steenwinckel
MAGIC: Mining an Augmented Graph using INK, starting from a CSV
SemTab
MAGIC
hybridINK, lookup
independent
none
SemTab2021
imec
CSV
Wikidata - CEA,CTA,CPA
2021
Wang
TCN: Table Convolutional Network for Web Table Interpretation
WWW
TCN
supTransformer
independent
none
custom dataset music domain
NotSpecified
2021
Yang
GBMTab: A Graph-Based Method for Interpreting Noisy Semantic Table to Knowledge Graph
SemTab
GBMTab
supPGM
independent
none
SemTab2021
NotSpecified
CSV
Wikidata
CEA,CTA
2021
Zhou
Tabular Data Concept Type Detection Using Star-Transformers
CIKM
supStar-Transformers
independent
none
custom dataset
NotSpecified
2020
Abdelmageed
JenTab: Matching Tabular Data to Knowledge Graphs
SemTab
JenTab
unsupfeatures
independent
none
Semtab2020
MIT
CSV
Wikidata
CEA,CTA,CPA
2020
Azzi
AMALGAM: making tabular dataset explicit with knowledge graph
SemTab
AMALGAM
unsupfeatures
independent
none
Semtab2020
NotSpecified
CSV
Wikidata
CEA,CTA
2020
Baazouzi
Kepler-aSI : Kepler as A Semantic Interpreter
SemTab
KEPLER-ASI
unsupfeatures
independent
none
Semtab2020
NotSpecified
CSV
Wikidata
CTA
2020
Chen
LinkingPark: An Integrated Approach for Semantic Table Interpretation
SemTab
LinkingPark
unsupfeatures
independent
none
Semtab2020
NotSpecified
CSV
Wikidata - ElasticSearch
CEA,CTA,CPA
2020
Cremaschi
A fully automated approach to a complete Semantic Table Interpretation
FGCS
MantisTable
unsupfeatures
independent
Fully-automated
Semtab2019, T2D, Limaye
Apache 2.0
CSV
DBpedia
CEA,CTA,CPA
2020
Cremaschi
MantisTable SE: an Efficient Approach for the Semantic Table Interpretation
SemTab
MantisTable SE
unsupfeatures
independent
none
Semtab2020
Apache 2.0
CSV
DBpedia,Wikidata - LamAPI
CEA,CTA,CPA
2020
Eslahi
Annotating Web Tables through Knowledge Bases: A Context-Based Approach
SDS
hybridfeatures & embeddings
independent
Limaye, T2D
NotSpecified
Web table
Wikidata
2020
Guo
Web Table Column Type Detection Using Deep Learning and Probability Graph Model
WISA
supNeural Network + CRF
independent
none
T2D, Limaye
NotSpecified
2020
Huynh
DAGOBAH: Enhanced Scoring Algorithms for Scalable Annotations of Tabular Data
SemTab
DAGOBAH SL 2020
hybridfeatures + embeddings, matching
independent
none
Semtab2020
NotSpecified
CSV
Wikidata - Spark dataframes
2020
Khurana
Semantic Annotation for Tabular Data
CIKM
C²
supMaximum Likelihood Estimation (MLE) through ensembles
independent
none
Limaye, Semantification, SemTab rounds from 1 to 4, T2Dv2, ISWC17
NotSpecified
2020
Kim
Generating Conceptual Subgraph from Tabular Data for Knowledge Graph Matching
SemTab
SSL
unsupfeatures
independent
none
Semtab2020
NotSpecified
CSV
Wikidata
CEA,CTA,CPA
2020
Li
Deep Entity Matching with Pre-Trained Language Models
VLDB
Ditto
supBERT, DistilBERT, RoBERTa, XLNet
independent
none
Entity Resolution benchmark, the Magellan dataset, WDC product matching dataset
Apache 2.0
2020
Nguyen
MTab4Wikidata at SemTab 2020: Tabular Data Annotation with Wikidata
SemTab
Mtab4Wikidata
unsupfeatures
independent
none
Semtab2020
NotSpecified
CSV
Wikidata - HashTable + Sparse Matrix
CEA,CTA,CPA
2020
Shigapov
bbw: Matching CSV to Wikidata via Meta-lookup
SemTab
bbw (boosted by wiki)
unsupfeatures
independent
none
Semtab2020
MIT
CSV
Wikidata - SeerX metasearch API
CEA,CTA,CPA
2020
Tyagi
LexMa: Tabular Data to Knowledge Graph Matching using Lexical Techniques
SemTab
LexMa
unsuplookup
independent
none
Semtab2020
NotSpecified
CSV
Wikidata
CTA,CPA
2020
Yumusak
Knowledge graph matching with inter-service information transfer
SemTab
TeamTR
unsupfeatures
independent
none
Semtab2020
NotSpecified
CSV
Wikidata
CTA,CPA
2020
Zhang
Novel Entity Discovery from Web Tables
WWW
suplexical + semantic features
independent
none
T2D, W2D, T2Dv2
CCA 4.0
CSV
DBpedia
2019
Chabot
DAGOBAH: An End-to-End Context-Free Tabular Data Semantic Annotation System
SemTab
DAGOBAH
hybridRule Base & Embeddings
independent
none
SemTab2019
Orange
Tables
DBpedia
RDF
2019
Chen
ColNet: Embedding the Semantics of Web Tables for Column Type Prediction
AAAI
ColNet
hybridCNN
independent
none
The method is evaluated with DBpedia and two different web table datasets, T2Dv2 from the general Web and Limaye from Wikipedia pages
Apache 2.0
Tables
DBpedia
NE and entity linking
2019
Chen
Learning Semantic Annotations for Tabular Data
IJCAI
ColNet
unsupCNN
independent
none
T2D, Limaye, Efthymiou
Apache 2.0
Tables
DBpedia
2019
Cremaschi
MantisTable: an Automatic Approach for the Semantic Table Interpretation
SemTab
MantisTable
unsupfeatures
independent
Fully-automated
Challenge rounds
Apache 2.0
2019
Hulsebos
Sherlock: A Deep Learning Approach to Semantic Data Type Detection
SIGKDD
Sherlock
supNeural network
independent
none
T2D
MIT
CSV
DBpedia
2019
Kruit
Extracting Novel Facts from Tables for Knowledge Graph Completion
ISWC
TAKCO
hybridPGM + features
independent
none
T2Dv2, Webaroo
MIT
Tables
DBpedia,Wikidata
New facts to complete KGs
2019
Morikawa
Semantic Table Interpretation using LOD4ALL
SemTab
LOD4ALL
unsupfeatures
independent
none
SemTab2019
NotSpecified
Tables
DBpedia - ElasticSearch
CEA,CTA,CPA
2019
Nguyen
MTab: Matching Tabular Data to Knowledge Graph using Probability Models
SemTab
MTab
unsupfeatures
independent
none
SemTab2019
NotSpecified
vertical relational table.
DBpedia
CEA,CTA,CPA
2019
Oliveira
ADOG - Annotating Data with Ontologies and Graphs
SemTab
ADOG
unsupfeatures
independent
none
NotSpecified
ontology, KG and Table
DBpedia - ArangoDB + ElasticSearch
CEA,CTA,CPA
2019
Steenwinckel
CSV2KG: Transforming Tabular Data into Semantic Knowledge
SemTab
CSV2KG
unsuplookup
independent
none
Semtab2019
NotSpecified
CSV
DBpedia
CEA,CTA,CPA
2019
Takeoka
Meimei: An Efficient Probabilistic Approach for Semantically Annotating Tables
AAAI
meimei
supMarkov Network
independent
none
Private company dataset
NotSpecified
CSV
WordNet
2019
Thawani
Entity Linking to Knowledge Graphs to Infer Column Types and Properties
SemTab
unsupfeatures
independent
none
Semtab2019
MIT
CSV
ElasticSearch
2019
Zhang
Sato: Contextual Semantic Type Detection in Tables
VLDB
Sato
supmulti-layer NN + LDA topic modeling
independent
none
T2Dv2
Apache 2.0
DBpedia
2018
Kacprzak
Making Sense of Numerical Data - Semantic Labelling of Web Tables
EKAW
NUMER
unsupfeatures
independent
none
MLL
MIT
DBpedia
2018
Luo
Cross-Lingual Entity Linking for Web Tables
AAAI
supneural network
independent
none
NotSpecified
Tables
Wikipedia
2018
Zhang
Ad Hoc Table Retrieval using Semantic Similarity
WWW
STR
unsupneural network
independent
none
TabEL
NotSpecified
2017
Efthymiou
Matching Web Tables with Knowledge Base Entities: From Entity Lookups to Entity Embeddings
ISWC
hybridHybrid
independent
none
TD2, Limaye, Wikipedia (a GS constructed by the authors created by extracting the hyperlinks of existing Wikipedia tables to Wikipedia pages, which we have replaced with annotations to the corresponding entities from the October 2015 version of DBpedia.) Since the header rows in Wikipedia tables are not linked to properties, our gold standard does not contain schema-level mappings.
NotSpecified
Web tables
JSON
2017
Ell
Towards a Large Corpus of Richly Annotated Web Tables for Knowledge Base Population
LD4IE
This paper is not about an apporach rather than on proposing techniques or hypothesis about the tables in order to improve STI approaches performance
unsuplookup
independent
none
WDC Web Table Corpus 2015
Apache 2.0
Web Tables
DBpedia - Labels + literals
2017
Zhang
Effective and Efficient Semantic Table Interpretation using TableMiner+
JOWS
TableMiner+
unsupprobabilistic features
independent
none
For evaluation, we compiled and annotated four datasets using Freebase: Limaye200, LimayeAll, IMDB and MusicBrainz.
Apache 2.0
Web tables
Freebase - rdf graph
2016
Ermilov
TAIPAN: Automatic Property Mapping for Tabular Data
EKAW
TAIPAN
unsuppattern
independent
none
Improved T2D
GPL 3.0
Not specified, they mention only tables. DBpedia Table Dataset (DBD)
DBpedia
2016
Neumaier
Multi-level semantic labelling of numerical values
ISWC
supHierarchical clustering (BKG)
independent
none
by splitting the DBpedia data into a test and training dataset.
Apache 2.0
CSV
DBpedia
2016
Pham
Semantic labeling: A domain-independent approach
ISWC
DSL(Domain-independent SemanticLabeler)
supLogistic Regression
independentMusum, city, soccer, weather
none
T2D
Apache 2.0
The input of our system is an unlabeled attribute and a set of labeled attributes as domain data.
The output is a set of top-k semantic types corresponding to the unlabeled attribute.
2016
Taheriyan
Learning the semantics of structured data sources
JOWS
Karma
supCosine similarity + statistical hypothesis
dependentmuseum
Fully-automated
Museum data, eventhough they say that the use some tables of museum data from the gold standard it does not mention which GS they use. The link to the datasets https://github.com/taheriyan/jws-knowledge-graphs-2015
Apache 2.0
XML files and JSON files. They can also import the domain ontologies they want to use for modeling the data. The system then automatically suggests a semantic model for the loaded source.
CIDOC-CRM,EDM
RDF
2016
Taheriyan
Leveraging Linked Data to Discover Semantic Relations within Data Sources
ISWC
Karma
suppattern
independent
Fully-automated
Apache 2.0
CSV, XML and JSON
CIDOC-CRM
a semantic model expressing how the assigned labels are connected
2015
Bhagavatula
TabEL: Entity Linking in Web Tables
ISWC
TabEL
supMarkov Network
independent
none
TabEL
CCA 4.0
Web table (XML)
Yago
2015
Ramnandan
Assigning Semantic Labels to Data Sources
ESWC
SemanticTyper
supCRF
independent
Semi-automated
we used data from the museum domain consisting of 29 data sources in diverse formats from various art museums in the U.S. Semantic labels
Apache 2.0
CSV
training data with Lucene, not KG data
2015
Ritze
Matching HTML Tables to DBpedia
WIMS
T2K Match
unsupfeature
independent
none
T2D
Apache 2.0
Web Table (HTML)
DBpedia
2014
Sekhavat
Knowledge Base Augmentation using Tabular Data
LDOW
unsupprobabilistic model
independent
none
ClueWeb09 dataset
NotSpecified
Yago
2014
Taheriyan
A Scalable Approach to Learn Semantic Models of Structured Sources
IEEE
unsupfeatures
independent
Semi-automated
We evaluated our approach on a dataset of 29 museum data sources
NotSpecified
Multiple sources modeled using the EDM, AAC, SKOS, Dublin Core Metadata Terms, FOAF, ORE, and ElementsGr2 ontologies
2013
Buche
Fuzzy Web Data Tables Integration Guided by an Ontological and Terminological Resource
IEEE
ONDINE
unsuplookup
independentmicrobial risk, chemical risk, aeronautics
none
Custom, 90 tables
NotSpecified
Domain specific web tables
XML documents representing data tables; RDF annotations
2013
Cruz
GIVA: A Semantic Framework for Geospatial and Temporal Data Integration, Visualization, and Analytics
SIGSPATIAL
Giva
supAgreementMaker
dependent
none
NotSpecified
GML, KML, Shapefile, MapInfo TAB, HTML table
2013
Deng
Scalable Column Concept Determination for Web Tables Using Large Knowledge Bases
VLDB
lookup
unsup
independent
none
NotSpecified
Web
DBpedia,Freebase,Yago
2013
Ermilov
User-driven Semantic Mapping of Tabular Data
I-SEMANTICS
pattern
independent
Semi-automated
NotSpecified
CSV, TSV, XLS, XLSX
RDF
2013
Mulwad
Semantic Message Passing for Generating Linked Data from Tables
ISWC
supMarkov Network
independent
none
Web Manual, Web Relation, Wiki Manual, Wiki Links
NotSpecified
Web and Wikipedia HTML tables
DBpedia,Yago,Wikitology
RDF
2013
Munoz
Triplifying Wikipedia's Tables
LD4IE
unsupexact match
independent
none
They extract 250 triples from the set and manually annotate them to produce a GS to test the approach on.
NotSpecified
Wikipedia tables
DBpedia
RDF
2013
Quercini
Entity Discovery and Annotation in Tables
EDBT
unsuplookup
independent
none
NotSpecified
Google Fusion Tables
DBpedia
2013
Zhang
InfoGather+: Semantic Matching and Annotation of Numeric and Time-Varying Attributes in Web Tables
SIGMOD
InfoGather+
unsupfeatures
independent
Semi-automated
Experiments conducted on three real-life datasets of web tables,extracted from a recent snapshot of Microsoft Bing search engine
NotSpecified
EAB (entity-attribute binary relationships) HTML Web tables
2013
Zwicklbauer
Towards Disambiguating Web Tables
ISWC
unsupfeatures
independent
none
Subset of Limaye
NotSpecified
DBpedia
2012
Goel
Exploiting Structure within Data for Accurate Labeling using Conditional Random Fields
ICAI
supCRF
dependentWeather forecast, flight status and geocoding
none
NotSpecified
Web tables
2012
Knoblock
Semi-automatically Mapping Structured Sources into the Semantic Web
ESWC
Karma
supCRF
independent
Semi-automated
Apache 2.0
Data sources Ontologies Semantic Types (training dataset)
Personal ontologies
Source model (used to generate RDF)
2012
Pimplikar
Answering Table Queries on the Web using Column Keywords
VLDB
unsupprobabilistic graphical model
independent
none
NotSpecified
HTML tables
2012
Wang
Understanding Tables on the Web
ER
unsuppattern matching
independent
none
Custom, 200 wikipedia tables
NotSpecified
HTML tables
2011
Mulwad
Automatically Generating Government Linked Data from Tables
AAAI
supMarkov Network + PGM
independent
Semi-automated
Custom GS, 15 tables
NotSpecified
CSV, XML
DBpedia,Freebase,WordNet,Yago
N3
2011
Venetis
Recovering Semantics of Tables on the Web
VLDB
unsuplookup
independent
Semi-automated
Custom GS
NotSpecified
HTML tables
Yago
2010
Limaye
Annotating and Searching Web Tables Using Entities, Types and Relationships
VLDB
unsupfeatures
independent
Fully-automated
NotSpecified
Web Table
Yago
2010
Mulwad
T2LD: Interpreting and Representing Tables as Linked Data⋆
ISWC
T2LD
supSVM
independent
none
NotSpecified
Web tables
Wikitology
N3
2010
Syed
Exploting a Web of Semantic Data for Interpreting Tables
WSC
Wikitology
unsuplookup
independent
none
NotSpecified
Wikipedia tables
Wikitology - Lucene for concepts
2009
Hignette
Fuzzy Annotation of Web Data Tables Driven by a Domain Ontology
ESWC
unsupsimilarity
independent
none
NotSpecified
Web table (XML)
Personal ontologies
RDF
2009
Tao
Automatic hidden-web table interpretation, conceptualization, and semantic annotation