A fully automated approach to a complete Semantic Table Interpretation

Cremaschi, Marco; Paoli, Flavio De; Rula, Anisa; Spahiu, Blerina

doi:10.1016/j.future.2020.05.019

Cited by 27 publications

(28 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We contacted the authors of MTab [9], CVS2KG [13], and Tabularisi [12], the tools that performed the best, but their tools were not publicly available. Only the authors of MantisTable [1], winner of the outstanding improvement award at SemTab 2019 (CEA task), provided us with a prototype of their tool. 11 Since the performance obtained by all the tools were similar to each other, we think that MantisTable is a good representative for the evaluation.…”

Section: Discussionmentioning

confidence: 99%

Tough Tables: Carefully Evaluating Entity Linking for Tabular Data

Cutrona

Bianchi

Jiménez-Ruiz

et al. 2020

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Table annotation is a key task to improve querying the Web and support the Knowledge Graph population from legacy sources (tables). Last year, the SemTab challenge was introduced to unify different efforts to evaluate table annotation algorithms by providing a common interface and several general-purpose datasets as a ground truth. The SemTab dataset is useful to have a general understanding of how these algorithms work, and the organizers of the challenge included some artificial noise to the data to make the annotation trickier. However, it is hard to analyze specific aspects in an automatic way. For example, the ambiguity of names at the entity-level can largely affect the quality of the annotation. In this paper, we propose a novel dataset to complement the datasets proposed by SemTab. The dataset consists of a set of highquality manually-curated tables with non-obviously linkable cells, i.e., where values are ambiguous names, typos, and misspelled entity names not appearing in the current version of the SemTab dataset. These challenges are particularly relevant for the ingestion of structured legacy sources into existing knowledge graphs. Evaluations run on this dataset show that ambiguity is a key problem for entity linking algorithms and encourage a promising direction for future work in the field.

show abstract

Section: Discussionmentioning

confidence: 99%

Tough Tables: Carefully Evaluating Entity Linking for Tabular Data

Cutrona

Bianchi

Jiménez-Ruiz

et al. 2020

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…Other unsupervised entity matching approaches adopt an iterative method that combines schema and entity matching. T2K [7] brought outstanding improvements in the state-of-the-art and inspired different systems [8,10]. The disambiguation component in the aforementioned approaches is dependant on the type-based constraints, which are assumed as hard constraints.…”

Section: Related Workmentioning

confidence: 99%

“…We found two patterns used by CEA algorithms available in the literature that can be improved by better handling entity types: (i) Filtering by type, where types associated to a column are used as hard constraints to filter out candidate entities having different types; (ii) Ranking by distributed entity representations similarity, where distributed representations of entities (i.e., entity embeddings) are used to compute the similarity between candidates for different labels in order to support the disambiguation. These patterns are, for example, core mechanisms used by a state-of-the-art algorithms such as FactBase, EmbeddingsOnGraph, and their hybrid combinations [6], T2K [7], TableMiner+ [8], but also in more recent approaches tailored on STI challenge data [5,9,10].…”

Section: Introductionmentioning

confidence: 99%

“…We tested our re-implemented versions on T2D -used in the original work -observing low performance compared with the original results. 10 In our opinion, the performance decrease is due to the following factors:…”

mentioning

confidence: 99%

“…Algorithms To demonstrate the generality of NEST, we looked for algorithms in literature to use in our experiments. However, just a few CEA algorithms are open-source, with some limitations (e.g., MantisTable [10] has scalability issues; the repository of CSV2KG [22] is incomplete. Authors of the best performing systems in SemTab 2019 (MTab [5], Tabularisi [11], and CSV2KG [22]) reported that their systems were not ready to be released.…”

mentioning

confidence: 99%

See 2 more Smart Citations

NEST: Neural Soft Type Constraints to Improve Entity Linking in Tables

Cutrona

Puleri

Bianchi

et al. 2021

Studies on the Semantic Web

View full text Add to dashboard Cite

Matching tables against Knowledge Graphs is a crucial task in many applications. A widely adopted solution to improve the precision of matching algorithms is to refine the set of candidate entities by their type in the Knowledge Graph. However, it is not rare that a type is missing for a given entity. In this paper, we propose a methodology to improve the refinement phase of matching algorithms based on type prediction and soft constraints. We apply our methodology to state-of-the-art algorithms, showing a performance boost on different datasets.

show abstract

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

A fully automated approach to a complete Semantic Table Interpretation

Cited by 27 publications

References 26 publications

Tough Tables: Carefully Evaluating Entity Linking for Tabular Data

Tough Tables: Carefully Evaluating Entity Linking for Tabular Data

NEST: Neural Soft Type Constraints to Improve Entity Linking in Tables

Table understanding: Problem overview

Contact Info

Product

Resources

About