Minicursos Da ERCEMAPI 2021 2021
DOI: 10.5753/sbc.7973.3.1
|View full text |Cite
|
Sign up to set email alerts
|

PLN: Das Técnicas Tradicionais aos Modelos de Deep Learning

Abstract: With the massive amount of data generated daily on the Web, researchers in the field of Natural Language Processing have focused on extracting useful information from unstructured data. This volume of data makes it impractical for anyone to manually process them in order to extract meaningful information, i.e., feelings, opinions, irony, hate speech, fake news, and others. The main objective of this short course is to introduce principles, traditional techniques, and tools in the field of NLP, developing model… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
4
0

Year Published

2023
2023
2023
2023

Publication Types

Select...
2

Relationship

0
2

Authors

Journals

citations
Cited by 2 publications
(4 citation statements)
references
References 12 publications
0
4
0
Order By: Relevance
“…This is because the corpus is unbalanced, i.e., a few non-ironic tweets concerning ironic ones. To mitigate this problem and inspired by the PiLN team [Anchiêta et al 2021], which adopts…”
Section: Resultsmentioning
confidence: 99%
See 2 more Smart Citations
“…This is because the corpus is unbalanced, i.e., a few non-ironic tweets concerning ironic ones. To mitigate this problem and inspired by the PiLN team [Anchiêta et al 2021], which adopts…”
Section: Resultsmentioning
confidence: 99%
“…[ Anchiêta et al 2021] developed an approach based on superficial features as Text Frequency-Inverse Document Frequency (TF-IDF) and fed the Support Vector Machine (SVM) classifier to identify ironic texts. Also, the authors used back-translation as data augmentation to balance the corpus.…”
Section: Related Workmentioning
confidence: 99%
See 1 more Smart Citation
“…The initial steps consist of acquiring the documents that will be used as a base in the classification process, provided by the Talentos Carreira RH platform, documents related to job requirements and resumes of anonymous participants in the process. After obtaining the corpus of terms belonging to the resumes job experience sections and job descriptions, the terms are pre-processed using the NLTK and Spacy libraries [Anchiêta et al 2021] to fulfill pre-processing steps related to:…”
Section: Implementation Steps 341 Acquisition and Pre-processingmentioning
confidence: 99%