Relation Extraction from Tables using Artificially Generated Metadata
Relation Extraction (RE) from tables is the task of identifying relations between pairs of columns of a table. Generally, RE models for this task require labelled tables for training. These labelled tables can also be generated artificially from a Knowledge Graph (KG), which makes the cost to acquire them much lower in comparison to manual annotations. However, unlike real tables, these synthetic tables lack associated metadata, such as, column-headers, captions, etc; this is because synthetic tables are created out of KGs that do not store such metadata. Meanwhile, previous works have shown that metadata is important for accurate RE from tables. To address this issue, we propose methods to artificially create some of this metadata for synthetic tables. Afterward, we experiment with a BERT-based model, in line with recently published works, that takes as input a combination of proposed artificial metadata and table content. Our empirical results show that this leads to improvements of 9\%-45\% in F1 score, in absolute terms, over 2 tabular datasets.
Code (0)
등록된 구현이 없습니다.
Tasks
RelationRelation ExtractionSimilar Papers 제목 키워드 기반
Relation Extraction from Tables using Artificially Generated Metadata
Relation Extraction (RE) from tables is the task of identifying relations between pairs of columns of a table. Generally, RE models for this task require labelled tables for training. These labelled tables can also be ge…
RelationRelation ExtractionA Relation Extraction Dataset for Knowledge Extraction from Web Tables
Relational web-tables are significant sources of structural information that are widely used for relation extraction and population of facts into knowledge graphs. To transform the web-table data into knowledge, we need …
Knowledge GraphsRelationRelation ExtractionSALT-KG: A Benchmark for Semantics-Aware Learning on Enterprise Tables
Building upon the SALT benchmark for relational prediction (Klein et al., 2024), we introduce SALT-KG, a benchmark for semantics-aware learning on enterprise tables. SALT-KG extends SALT by linking its multi-table transa…
The CTU Prague Relational Learning Repository
The aim of the Prague Relational Learning Repository is to support machine learning research with multi-relational data. The repository currently contains 148 SQL databases hosted on a public MySQL server located at http…
BIG-bench Machine LearningRelational ReasoningPIPER: Content-Based Table Search via profiling and LLM-Generated Pseudoqueries
The rapid growth of tabular datasets in data lakes, data spaces, and open data portals makes effective dataset search essential for reuse and analysis. Existing search systems rely mainly on metadata, which is often inco…
Question Answering