Towards holistic Entity Linking: Survey and directions

Oliveira, Italo Lopes; Fileto, Renato; Speck, René; García, L.; Moussallem, Diego; Lehmann, Jens

doi:10.1016/j.is.2020.101624

Cited by 25 publications

(21 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We analyse different recent and older surveys on EL and highlight specific areas which are not covered as well as our survey's novelties (see also Section 8). While some very recent surveys exist [2,81,101], they do not consider the different underlying Knowledge Graphs as a significant factor affecting the performance of EL approaches. Furthermore, barely any approaches included in other surveys are working on Wikidata and take the particular characteristics of Wikidata into account (see Section 7).…”

Section: Criteria Must Satisfy Allmentioning

confidence: 99%

See 1 more Smart Citation

Survey on English Entity Linking on Wikidata: Datasets and approaches

Cedric

Lehmann

Usbeck

2022

Self Cite

View full text Add to dashboard Cite

Wikidata is a frequently updated, community-driven, and multilingual knowledge graph. Hence, Wikidata is an attractive basis for Entity Linking, which is evident by the recent increase in published papers. This survey focuses on four subjects: (1) Which Wikidata Entity Linking datasets exist, how widely used are they and how are they constructed? (2) Do the characteristics of Wikidata matter for the design of Entity Linking datasets and if so, how? (3) How do current Entity Linking approaches exploit the specific characteristics of Wikidata? (4) Which Wikidata characteristics are unexploited by existing Entity Linking approaches? This survey reveals that current Wikidata-specific Entity Linking datasets do not differ in their annotation scheme from schemes for other knowledge graphs like DBpedia. Thus, the potential for multilingual and time-dependent datasets, naturally suited for Wikidata, is not lifted. Furthermore, we show that most Entity Linking approaches use Wikidata in the same way as any other knowledge graph missing the chance to leverage Wikidata-specific characteristics to increase quality. Almost all approaches employ specific properties like labels and sometimes descriptions but ignore characteristics such as the hyper-relational structure. Hence, there is still room for improvement, for example, by including hyper-relational graph embeddings or type information. Many approaches also include information from Wikipedia, which is easily combinable with Wikidata and provides valuable textual information, which Wikidata lacks.

show abstract

Section: Criteria Must Satisfy Allmentioning

confidence: 99%

“…Another survey [81] examines recent approaches, which employ holistic strategies. Holism in the context of EL is defined as the usage of domain-specific inputs and metadata, joint ER-EL approaches, and collective disambiguation methods.…”

Section: Related Workmentioning

confidence: 99%

Survey on English Entity Linking on Wikidata: Datasets and approaches

Cedric

Lehmann

Usbeck

2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…Recently, short texts and especially queries within QASs have attracted more attention because of their limited context [ 1 , 46 ]. To perform a NED in queries, EARL [ 17 ] defines the context of the entity by observing the relations around it.…”

Section: Related Workmentioning

confidence: 99%

“…Other studies have measured the relationship between entities in the input text to link them collectively to the corresponding resources. Recently, short texts, and particularly queries in the QASs, have attracted attention because of their limited context [ 26 , 46 ]. However, because of the limited information they provide, textual similarity is not a sufficient solution.…”

Section: Introductionmentioning

confidence: 99%

Named entity disambiguation in short texts over knowledge graphs

2022

View full text Add to dashboard Cite

The ever-growing usage of knowledge graphs (KGs) positions named entity disambiguation (NED) at the heart of designing accurate KG-driven systems such as query answering systems (QAS). According to the current research, most studies dealing with NED on KGs involve long texts, which is not the case of short text fragments, identified by their limited contexts. The accuracy of QASs strongly depends on the management of such short text. This limitation motivates this paper, which studies the NED problem on KGs, involving only short texts. First, we propose a NED approach including the following steps: (i) context expansion using WordNet to measure its similarity to the resource context. (ii) Exploiting coherence between entities in queries that contain more than one entity, such as “Is Michelle Obama the wife of Barack Obama?”. (iii) Taking into account the relations between words to calculate their similarity with the properties of a resource. (iv) the use of syntactic features. The NED solution approach is compared to state-of-the-art approaches using five datasets. The experimental results show that our approach outperforms these systems by 27% in the F-measure. A system called Welink , implementing our proposal, is available on GitHub, and it is also accessible via a REST API.

show abstract

“…Entity Linking and Distant Supervision Solving the problem of typing entities can also be addressed by the methods of Entity Linking (EL), in which a diversity of string-matching techniques are employed to relate found mentions of NEs with known entities. Common tools for entity linking include DBPedia Spotlight [4], Entity Fishing [13] or Babelfly [14]; and the number of approaches to EL continues to increase (see [18] for a recent overview). EL, however, assumes the existence of a catalog of entities (preferably containing additional knowledge).…”

Section: Related Workmentioning

confidence: 99%

Annotating Entities with Fine-Grained Types in Austrian Court Decisions

Revenko¹,

Breit²,

Mireles³

et al. 2021

Studies on the Semantic Web

View full text Add to dashboard Cite

The usage of Named Entity Recognition tools on domain-specific corpora is often hampered by insufficient training data. We investigate an approach to produce fine-grained named entity annotations of a large corpus of Austrian court decisions from a small manually annotated training data set. We apply a general purpose Named Entity Recognition model to produce annotations of common coarse-grained types. Next, a small sample of these annotations are manually inspected by domain experts to produce an initial fine-grained training data set. To efficiently use the small manually annotated data set we formulate the task of named entity typing as a binary classification task – for each originally annotated occurrence of an entity, and for each fine-grained type we verify if the entity belongs to it. For this purpose we train a transformer-based classifier. We randomly sample 547 predictions and evaluate them manually. The incorrect predictions are used to improve the performance of the classifier – the corrected annotations are added to the training set. The experiments show that re-training with even a very small number (5 or 10) of originally incorrect predictions can significantly improve the classifier performance. We finally train the classifier on all available data and re-annotate the whole data set.

show abstract

Towards holistic Entity Linking: Survey and directions

Cited by 25 publications

References 36 publications

Survey on English Entity Linking on Wikidata: Datasets and approaches

Survey on English Entity Linking on Wikidata: Datasets and approaches

Named entity disambiguation in short texts over knowledge graphs

Annotating Entities with Fine-Grained Types in Austrian Court Decisions

Contact Info

Product

Resources

About