TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK	REMOVE
Column Type Annotation	ToughTables-WD	DAGOBAH	F1 (%)	40.9	# 5
Cell Entity Annotation	ToughTables-WD	DAGOBAH	F1 (%)	94.5	# 1

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/from-heuristics-to-language-models-a-journey/cell-entity-annotation-on-toughtables-wd)](https://paperswithcode.com/sota/cell-entity-annotation-on-toughtables-wd?p=from-heuristics-to-language-models-a-journey)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/from-heuristics-to-language-models-a-journey/column-type-annotation-on-toughtables-wd)](https://paperswithcode.com/sota/column-type-annotation-on-toughtables-wd?p=from-heuristics-to-language-models-a-journey)`

From Heuristics to Language Models: A Journey Through the Universe of Semantic Table Interpretation with DAGOBAH

SemTab@ISWC 2022 · Viet-Phi Huynh, Yoan Chabot, Thomas Labbé, Jixiong Liu and Raphaël Troncy ·

This paper presents DAGOBAH SL 2022, a semantic table interpretation system that has been continuously improved over the last four years when participating in the SemTab challenge. This year, we have improved the lookup coverage using external resources and we have integrated language models for better understanding the table headers. We have also implemented various system optimizations that lead to a reduction in execution time of about 30%. In this paper, we also show the relevance of using deep learning-based approaches for resolving certain ambiguities and we discuss the limitations of existing corpora and systems for maturing further this research field.

PDF