A Bootstrapping Approach for Training a NER with Conditional Random Fields

Teixeira, Jorge; Sarmento, Luís; Oliveira, Eugénio

doi:10.1007/978-3-642-24769-9_48

Cited by 12 publications

(7 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The pattern identified is vaguely the same for both news and Wikipedia data, and follows a structure of [CapitalizedSequence], [ergonym] just like in Teixeira et al, 2011. Some examples of words present in the ergonym list are: presidente, jogador, vocalista, pai, marido, mulher.…”

Section: Methodsmentioning

confidence: 82%

“…Annotated datasets are scarce and hard to obtain for most languages. Teixeira et al, 2011 concluded that HAREM datasets are not adequate to be used on an up-to-date NER system due to the age of the articles that compose the datasets. On the other hand, non annotated data or raw text is for the most part freely available with virtually no cost and a constant stream of fresh data.…”

Section: Bootstrappingmentioning

confidence: 99%

See 1 more Smart Citation

Applying Deep Neural Networks to Named Entity Recognition in Portuguese Texts

Fernandes

Cardoso

Oliveira

2018

2018 Fifth International Conference on Social Networks Analysis, Management and Security (SNAMS)

View full text Add to dashboard Cite

There is currently few research in using deep learning (DL) applied to Named Entities Recognition (NER) in Portuguese texts. This work exposes some challenges and limitations but also the benefits of applying DL architectures to NER in Portuguese. Four different DL architectures are applied to Portuguese datasets. All architectures are heavily influenced by previous published work in NER applied to English. Annotated data is used to train and test NER models, while non-annotated data is used to train word embeddings, as well as being a key part of a bootstrapping approach, where raw textual data is used to create NER models.

show abstract

Section: Methodsmentioning

confidence: 82%

Section: Bootstrappingmentioning

confidence: 99%

Applying Deep Neural Networks to Named Entity Recognition in Portuguese Texts

Fernandes

Cardoso

Oliveira

2018

2018 Fifth International Conference on Social Networks Analysis, Management and Security (SNAMS)

View full text Add to dashboard Cite

show abstract

“…Bootstrapping approaches were originally used as a method of extracting terms through the recognition of patterns [31]- [33]. In [34] and [35], bootstrapping algorithms are used to automatically label unlabeled data. This data is then used for an NER.…”

Section: Term Extraction With Ner For Nl Requirementsmentioning

confidence: 99%

Extraction of System States from Natural Language Requirements

Pudlitz

Brokhausen

Vogelsang

2019

2019 IEEE 27th International Requirements Engineering Conference (RE)

View full text Add to dashboard Cite

In recent years, simulations have proven to be an important means to verify the behavior of complex software systems. The different states of a system are monitored in the simulations and are compared against the requirements specification. So far, system states in natural language requirements cannot be automatically linked to signals from the simulation. However, the manual mapping between requirements and simulation is a time-consuming task. Named-entity Recognition is a sub-task from the field of automated information retrieval and is used to classify parts of natural language texts into categories. In this paper, we use a self-trained Named-entity Recognition model with Bidirectional LSTMs and CNNs to extract states from requirements specifications. We present an almost entirely automated approach and an iterative semi-automated approach to train our model. The automated and iterative approach are compared and discussed with respect to the usual manual extraction. We show that the manual extraction of states in 2,000 requirements takes nine hours. Our automated approach achieves an F1-score of 0.51 with 15 minutes of manual work and the iterative approach achieves an F1-score of 0.62 with 100 minutes of work.

show abstract

“…"Barack Obama, president of USA") and linguistic patterns well defined for the journalistic text style. We use a bootstrap approach to train the NER system [11]. Our method starts by annotating persons names on a dataset of 50,000 news items.…”

Section: News Processing Pipelinementioning

confidence: 99%

“…TimeMachine, as a computational journalism tool, brings together a set of Natural Language Processing, Text Mining and Information Retrieval technologies to automatically extract and index entity related knowledge from the news articles [5][6][7][8][9][10][11]. It allows users to issue queries containing keywords and phrases about news stories or events, and retrieves the most relevant entities mentioned in the news articles through time.…”

Section: Introductionmentioning

confidence: 99%

TimeMachine: Entity-Centric Search and Visualization of News Archives

Saleiro

Teixeira

Soares

et al. 2016

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Abstract. We present a dynamic web tool that allows interactive search and visualization of large news archives using an entity-centric approach. Users are able to search entities using keyword phrases expressing news stories or events and the system retrieves the most relevant entities to the user query based on automatically extracted and indexed entity profiles. From the computational journalism perspective, TimeMachine allows users to explore media content through time using automatic identification of entity names, jobs, quotations and relations between entities from co-occurrences networks extracted from the news articles. TimeMachine demo is available at http://maquinadotempo.sapo.pt/.

show abstract

A Bootstrapping Approach for Training a NER with Conditional Random Fields

Cited by 12 publications

References 9 publications

Applying Deep Neural Networks to Named Entity Recognition in Portuguese Texts

Applying Deep Neural Networks to Named Entity Recognition in Portuguese Texts

Extraction of System States from Natural Language Requirements

TimeMachine: Entity-Centric Search and Visualization of News Archives

Contact Info

Product

Resources

About