Filters








4 Hits in 1.4 sec

TabVec: Table Vectors for Classification of Web Tables [article]

Majid Ghasemi-Gol, Pedro Szekely
2018 arXiv   pre-print
There are hundreds of millions of tables in Web pages that contain useful information for many applications.  ...  TabVec deploys syntax and semantics of table cells, and embeds the structure of tables in a table vector space.  ...  Table vectors created by TabVec embed structure of web tables, and can be used to cluster tables according to their structural features.  ... 
arXiv:1802.06290v1 fatcat:ehogpj3ihbfvpf5uhthtzfyai4

DeepTable: a permutation invariant neural network for table orientation classification

Maryam Habibi, Johannes Starlinger, Ulf Leser
2020 Data mining and knowledge discovery  
In this paper, we address the problem of classifying a given table into one of the three layouts horizontal (for row tables), vertical (for column tables), and matrix.  ...  In a second evaluation, we manually labeled a corpus of 300 tables and were able to confirm DeepTable to reach superior performance in the table layout classification task.  ...  Compliance with ethical standards Conflict of interest The authors declare that they have no conflict of interest.  ... 
doi:10.1007/s10618-020-00711-x fatcat:unffmwctgfcwrkzuldcowzcsgm

ChemTables: a dataset for semantic classification on tables in chemical patents

Zenan Zhai, Christian Druckenbrodt, Camilo Thorne, Saber A Akhondi, Dat Quoc Nguyen, Trevor Cohn, Karin Verspoor
2021
For developing and evaluating methods for the table classification task, we developed a new dataset, called CHEMTABLES, which consists of 788 chemical patent tables with labels of their content type.  ...  We further establish strong baselines for the table classification task in chemical patents by applying state-of-the-art neural network models developed for natural language processing, including TabNet  ...  Ghasemi-Gol M, Szekely P (2018) TabVec: table vectors for classification of 162–174 .  ... 
doi:10.1186/s13321-021-00568-2 pmid:34895295 pmcid:PMC8665561 fatcat:t4jcrlkbabav5n3suy4qsgvf5y

Joint Verification and Reranking for Open Fact Checking Over Tables

Michael Sejr Schlichtkrull, Vladimir Karpukhin, Barlas Oguz, Mike Lewis, Wen-tau Yih, Sebastian Riedel
2021 Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)   unpublished
Structured information is an important knowledge source for automatic verification of factual claims.  ...  Our open-domain model achieves performance comparable to the closed-domain stateof-the-art on the TabFact dataset, and demonstrates performance gains from the inclusion of multiple tables as well as a  ...  Acknowledgments We would like to thank Fabio Petroni and Nicola De Cao for helpful discussions and comments.  ... 
doi:10.18653/v1/2021.acl-long.529 fatcat:dj3jsky6jvdi3fxz3fb3rvrcgq