Multi-modal Information Extraction from Text, Semi-structured, and Tabular Data on the Web

Dong, Xin Luna; Hajishirzi, Hannaneh; Lockard, Colin; Shiralkar, Prashant

doi:10.1145/3394486.3406468

Cited by 10 publications

(6 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The current limitations and open challenges in the TU research were discussed in the recent surveys (Roldán et al, 2020; Zhang and Balog, 2020; Bonfitto et al, 2021) and tutorials (Burdick et al, 2020; Dong et al, 2020; Pujara et al, 2021). This overview continues the discussion by pointing out how the existing statements of the TU tasks ignore the complexity and diversity of real‐world tables.…”

Section: Current Limitations and Future Directionsmentioning

confidence: 99%

See 1 more Smart Citation

Table understanding: Problem overview

Shigarov

2022

WIREs Data Min & Knowl

View full text Add to dashboard Cite

Tables are probably the most natural way to represent relational data in various media and formats. They store a large number of valuable facts that could be utilized for question answering, knowledge base population, natural language generation, and other applications. However, many tables are not accompanied by semantics for the automatic interpretation of the information they present. Table Understanding (TU) aims at recovering the missing semantics that enables the extraction of facts from tables. This problem covers a range of issues from table detection in document images to semantic table interpretation with the help of external knowledge bases. To date, the TU research has been ongoing on for 30 years. Nevertheless, there is no common point of view on the scope of TU; the terminology still needs agreement and unification. In recent years, science and technology have shown a rapidly increasing interest in TU. Nowadays, it is especially important to check the meaning of this research problem once again. This article gives a comprehensive characterization of the TU problem, including a description of its subproblems, tasks, subtasks, and applications. It also discusses the common limitations used in the existing problem statements and proposes some directions for further research that would help overcome the corresponding limitations. This article is categorized under: Algorithmic Development > Text Mining Algorithmic Development > Web Mining

show abstract

Section: Current Limitations and Future Directionsmentioning

confidence: 99%

“…The early proposals were reviewed by Zanibbi et al (2004), Embley et al (2006), and e Silva et al (2006). Many new advancements have been considered in the recent surveys (Zhang and Balog, 2020; Roldán et al, 2020; Bonfitto et al, 2021) and tutorials (Burdick et al, 2020; Dong et al, 2020; Pujara et al, 2021).…”

Section: Introductionmentioning

confidence: 99%

Table understanding: Problem overview

Shigarov

2022

WIREs Data Min & Knowl

View full text Add to dashboard Cite

show abstract

“…It is not surprising then that they are considered one of the most significant information sources in the current Web [4]. The information in typical HTML tables can be leveraged in many application domains [2,[4][5][6][7][8], e.g., knowledge management, information retrieval, web mining, summarisation, knowledge base construction, or question answering. Researchers commonly refer to the tables that are used to display information as relational tables, in contrast to nonrelational tables that are used to position other elements on the screen.…”

Section: Introductionmentioning

confidence: 99%

A coral-reef approach to extract information from HTML tables

Jiménez

Roldán

Corchuelo

2022

Applied Soft Computing

View full text Add to dashboard Cite

“…O artigo também utiliza reconhecimento da entidades ou tags de dados para identificac ¸ão de coordenadas úteis para o dataset proposto, conforme apresentado na Figura 1. Embora pesquisas abordem a extrac ¸ão de dados Web para problemas diferentes as dificuldades são semelhantes, como identificar dados relevantes para o domínio investigado [Dong et al 2020]. O artigo propõe uma alternativa para a criac ¸ão de um dataset a partir do enriquecimento com arquivos de dados georreferenciados.…”

Section: Introduc ¸ãOunclassified

Um Dataset Enriquecido com Dados Extraídos da Web para Aplicações de Georreferenciamento

Clovis

Dorneles

2022

Anais Do IV Dataset Showcase Workshop (DSW 2022)

View full text Add to dashboard Cite

Aplicações agrícolas e ambientais dependem de dados georreferenciados. A obtenção desse tipo de dado exige recursos elevados relacionados a hardware e recursos humanos especializados. A extração de dados da Web pode ser uma alternativa viável para criação de datasets para essa demanda. É possível encontrar repositórios públicos em ambiente Web para criar ou complementar datasets no domínio agrícola e ambiental, seja para delimitação de áreas agrícolas ou identificação e monitoramento de áreas ambientais. O presente artigo apresenta uma proposta para extração de dados da Web com o objetivo de criar um dataset para uso agrícola e ambiental por meio da extração de geo-coordenadas em repositórios públicos.

show abstract

Multi-modal Information Extraction from Text, Semi-structured, and Tabular Data on the Web

Cited by 10 publications

References 6 publications

Table understanding: Problem overview

Table understanding: Problem overview

A coral-reef approach to extract information from HTML tables

Um Dataset Enriquecido com Dados Extraídos da Web para Aplicações de Georreferenciamento

Contact Info

Product

Resources

About