Boosting Named Entity Recognition with Neural Character Embeddings

Santos, Cícero Nogueira dos; Guimarães, Victor Hugo Dantas

doi:10.48550/arxiv.1505.05008

Cited by 7 publications

(9 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Word embeddings are able to capture syntactic and semantic information, yet for tasks such as POS-tagging and NER, intraword morphological and shape information can also be very useful. Generally speaking, building natural language understanding systems at the character level has attracted certain research attention [29,30,31,32]. Better results on morphologically rich languages are reported in certain NLP tasks.…”

Section: Character Embeddingsmentioning

confidence: 99%

“…Better results on morphologically rich languages are reported in certain NLP tasks. Santos and Guimaraes [31] applied character-level representations, along with word embeddings for NER, achieving state-of-the-art results in Portuguese and Spanish corpora. Kim et al [29] showed positive results on building a neural language model using only character embeddings.…”

Section: Character Embeddingsmentioning

confidence: 99%

See 1 more Smart Citation

Recent Trends in Deep Learning Based Natural Language Processing [Review Article]

Young

Hazarika

Poria

et al. 2018

IEEE Comput. Intell. Mag.

2,813

1,307

View full text Add to dashboard Cite

Deep learning methods employ multiple processing layers to learn hierarchical representations of data, and have produced state-of-the-art results in many domains. Recently, a variety of model designs and methods have blossomed in the context of natural language processing (NLP). In this paper, we review significant deep learning related models and methods that have been employed for numerous NLP tasks and provide a walk-through of their evolution. We also summarize, compare and contrast the various models and put forward a detailed understanding of the past, present and future of deep learning in NLP.

show abstract

Section: Character Embeddingsmentioning

confidence: 99%

Section: Character Embeddingsmentioning

confidence: 99%

Recent Trends in Deep Learning Based Natural Language Processing [Review Article]

Young

Hazarika

Poria

et al. 2018

IEEE Comput. Intell. Mag.

2,813

1,307

View full text Add to dashboard Cite

show abstract

“…Dernoncourt et al [21] followed the same model architecture to train the NER. Similarly, Santos et al [22] obtained the word representation from characters by CNN and concatenated the embeddings of words before feeding to bidirectional LSTM. The Viterbi algorithm has also been used for inferencing for NER.…”

Section: Related Workmentioning

confidence: 99%

Development of a Dataset and a Deep Learning Baseline Named Entity Recognizer for Three Low Resource Languages: Bhojpuri, Maithili and Magahi

Mundotiya¹,

Kumar²,

Kumar³

et al. 2020

Preprint

View full text Add to dashboard Cite

In Natural Language Processing (NLP) pipelines, Named Entity Recognition (NER) is one of the preliminary problems, which marks proper nouns and other named entities such as Location, Person, Organization, Disease etc. Such entities, without a NER module, adversely affect the performance of a machine translation system. NER helps in overcoming this problem by recognising and handling such entities separately, although it can be useful in Information Extraction systems also. Bhojpuri, Maithili and Magahi are low resource languages, usually known as Purvanchal languages. This paper focuses on the development of a NER benchmark dataset for the Machine Translation systems developed to translate from these languages to Hindi by annotating parts of their available corpora. Bhojpuri, Maithili and Magahi corpora of sizes 228373, 157468 and 56190 tokens, respectively, were annotated using 22 entity labels.The annotation considers coarse-grained annotation labels followed by the tagset used in one of the Hindi NER datasets. We also report a Deep Learning based

show abstract

“…Instead of the standard F 1 score, we follow the evaluation proposed in [17], which consists of a modified First HAREM F 1 score used to compare different models. Our choice is based on its wide adoption in the Portuguese NER literature [18], [19], [20].…”

Section: B Evaluationmentioning

confidence: 99%

Building a Massive Corpus for Named Entity Recognition Using Free Open Data Sources

Menezes

Milidiú

Savarese

2019

2019 8th Brazilian Conference on Intelligent Systems (BRACIS)

View full text Add to dashboard Cite

With the recent progress in machine learning, boosted by techniques such as deep learning, many tasks can be successfully solved once a large enough dataset is available for training. Nonetheless, human-annotated datasets are often expensive to produce, especially when labels are fine-grained, as is the case of Named Entity Recognition (NER), a task that operates with labels on a word-level.In this paper, we propose a method to automatically generate labeled datasets for NER from public data sources by exploiting links and structured data from DBpedia and Wikipedia. Due to the massive size of these data sources, the resulting dataset -SESAME 1 -is composed of millions of labeled sentences. We detail the method to generate the dataset, report relevant statistics, and design a baseline using a neural network, showing that our dataset helps building better NER predictors.

show abstract

Boosting Named Entity Recognition with Neural Character Embeddings

Cited by 7 publications

References 0 publications

Recent Trends in Deep Learning Based Natural Language Processing [Review Article]

Recent Trends in Deep Learning Based Natural Language Processing [Review Article]

Development of a Dataset and a Deep Learning Baseline Named Entity Recognizer for Three Low Resource Languages: Bhojpuri, Maithili and Magahi

Building a Massive Corpus for Named Entity Recognition Using Free Open Data Sources

Contact Info

Product

Resources

About