Fine-grained Dutch named entity recognition

Desmet, Bart; Hoste, Véronique

doi:10.1007/s10579-013-9255-y

Cited by 19 publications

(29 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our research differs from the previous entity discovery studies [2,3,[9][10][11][12] introduced in Section 2.2 mainly in three points. First, we used a full text corpus rather than a single document or plain text to discover entities and their types.…”

mentioning

confidence: 79%

Turkish entity discovery with word embeddings

Kalender¹,

Korkmaz²

2017

Turk J Elec Eng & Comp Sci

View full text Add to dashboard Cite

Entity-linking systems link noun phrase mentions in a text to their corresponding knowledge base entities in order to enrich a text with metadata. Wikipedia is a popular and comprehensive knowledge base that is widely used in entity-linking systems. However, long-tail entities are not popular enough to have their own Wikipedia articles.Therefore, a knowledge base created by using Wikipedia entities would be limited to only popular entities. In order to overcome the knowledge base coverage limitation of Wikipedia-based entity-linking systems, this paper presents an entity-discovery system that can detect semantic types of entities that are not defined in Wikipedia. The effectiveness of the proposed system was validated empirically through the use of generated data sets for the Turkish language. The experimental results show that, in terms of accuracy, our system performs competitively in comparison to the previous methods in the literature. Its high performance is achieved through a method that learns word embeddings for candidate entities.

show abstract

mentioning

confidence: 79%

Turkish entity discovery with word embeddings

Kalender¹,

Korkmaz²

2017

Turk J Elec Eng & Comp Sci

View full text Add to dashboard Cite

show abstract

“…Extraction systems are used to identify elements in a text document that belong to predefined categories of entities and to extract relationships or associations among/between entities [14]. The main method for entity extraction is named entity recognition (NER): automatically identifying names in text and classifying them into predefined set of categories [13,15,16]. The most widely used categories are Person, Organization, Location, and Date.…”

Section: Entity Extractionmentioning

confidence: 99%

“…The most widely used categories are Person, Organization, Location, and Date. As domains of applications have grown, so have the entity categories, with such newer categories as Time, Facility, Equipment, Weapon, Animal, Plant, Medicine, Protein, and Gene, among many others [16]. Relationship extraction is the process of identifying two entities that are associated together within a text document.…”

Section: Entity Extractionmentioning

confidence: 99%

“…Rule-based systems define a set of rules that would determine the presence of an entity and its classification. The rules can be grammar-based, gazetteers of personal and company names, and higher level based, such as name co-reference [16,17]. Ontologies are also used to represent a group of related independent categories.…”

Section: Entity Extractionmentioning

confidence: 99%

“…In an unsupervised approach, entities are clustered based on the context or on entities' simultaneous occurrences (co-occurrence) in the source being analyzed [16]. However, as of now, these systems are not very accurate and many entities are missed.…”

Section: Machine Learningmentioning

confidence: 99%

See 2 more Smart Citations

Developing an innovative entity extraction method for unstructured data

Zaghloul¹,

Trimi

2017

Int J Qual Innov

View full text Add to dashboard Cite

The main goal of this study is to build high-precision extractors for entities such as Person and Organization as a good initial seed that can be used for training and learning in machine-learning systems, for the same categories, other categories, and across domains, languages, and applications. The improvement of entities extraction precision also increases the relationships extraction precision, which is particularly important in certain domains (such as intelligence systems, social networking, genetic studies, healthcare, etc.). These increases in precision improve the end users' experience quality in using the extraction system because it lowers the time that users spend for training the system and correcting outputs, focusing more on analyzing the information extracted to make better data-driven decisions.

show abstract

Medieval Spanish (12th–15th centuries) named entity recognition and attribute annotation system based on contextual information

Platas

Ros

González-Blanco³

et al. 2020

Asso for Info Science & Tech

View full text Add to dashboard Cite

The recognition of named entities in Spanish medieval texts presents great complexity, involving specific challenges: First, the complex morphosyntactic characteristics in proper-noun use in medieval texts. Second, the lack of strict orthographic standards. Finally, diachronic and geographical variations in Spanish from the 12th to 15th century. In this period, named entities usually appear as complex text structure. For example, it was frequent to add nicknames and information about the persons role in society and geographic origin. To tackle this complexity, named entity recognition and classification system has been implemented. The system uses contextual cues based on semantics to detect entities and assign a type. Given the occurrence of entities with attached attributes, entity contexts are also parsed to determine entitytype-specific dependencies for these attributes. Moreover, it uses a variant generator to handle the diachronic evolution of Spanish medieval terms from a phonetic and morphosyntactic viewpoint. The tool iteratively enriches its proper lexica, dictionaries, and gazetteers. The system was evaluated on a corpus of over 3,000 manually annotated entities of different types and periods, obtaining F1 scores between 0.74 and 0.87. Attribute annotation was evaluated for a person and role name attributes with an overall F1 of 0.75.

show abstract

Fine-grained Dutch named entity recognition

Cited by 19 publications

References 27 publications

Turkish entity discovery with word embeddings

Turkish entity discovery with word embeddings

Developing an innovative entity extraction method for unstructured data

Medieval Spanish (12th–15th centuries) named entity recognition and attribute annotation system based on contextual information

Contact Info

Product

Resources

About