• norsk
    • English
  • English 
    • norsk
    • English
  • Login
View Item 
  •   Home
  • Universitetet i Stavanger
  • Faculty of Science and Technology
  • Department of Electrical and Computer Engineering (TN-IDE)
  • Studentoppgaver (TN-IDE)
  • View Item
  •   Home
  • Universitetet i Stavanger
  • Faculty of Science and Technology
  • Department of Electrical and Computer Engineering (TN-IDE)
  • Studentoppgaver (TN-IDE)
  • View Item
JavaScript is disabled for your browser. Some features of this site may not work without it.

Table2Vec: Neural Word and Entity Embeddings for Table Population and Retrieval

Deng, Li
Master thesis
Thumbnail
View/Open
Deng_Li.pdf (2.497Mb)
URI
http://hdl.handle.net/11250/2564418
Date
2018-06
Metadata
Show full item record
Collections
  • Studentoppgaver (TN-IDE) [1026]
Abstract
Tables contain a significant amount of valuable knowledge in a structured form. In recent years, a growing body of studies related to tables has been conducted in different application domains. To the best of our knowledge, utilizing neural embeddings regarding table corpus is rather unexploited. In this thesis, our goal is to employ neural language modeling approaches to embed tabular data into vector spaces, which are leveraged and contributed to table-related tasks. Specifically, we consider different tabular data, such as sequences of words, table entities, core column entities, and heading labels in relational tables, for training word and entity embeddings.

These embeddings are utilized subsequently in three particular table-related tasks, i.e., row population, column population, and table retrieval, by incorporating them into existing retrieval models as additional semantic similarity signals. The main novel contribution of Table2Vec is a neural method for performing multiple table-related tasks developed specially on table corpus.

We further conduct an evaluation of table embeddings on the task level. The results show that Table2Vec can significantly and substantially improve upon the performance of state-of-the-art baselines. In the best case, Table2Vec outperforms the corresponding baseline by 40%.
Description
Master's thesis in Computer science
Publisher
University of Stavanger, Norway
Series
Masteroppgave/UIS-TN-IDE/2018;

Contact Us | Send Feedback

Privacy policy
DSpace software copyright © 2002-2019  DuraSpace

Service from  Unit
 

 

Browse

ArchiveCommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsDocument TypesJournalsThis CollectionBy Issue DateAuthorsTitlesSubjectsDocument TypesJournals

My Account

Login

Statistics

View Usage Statistics

Contact Us | Send Feedback

Privacy policy
DSpace software copyright © 2002-2019  DuraSpace

Service from  Unit