paper-with-me

홈 › Papers

Inferring the source of official texts: can SVM beat ULMFiT?

2020-03-02 · International Conference on Computational Processing of the Portuguese Language 2020 3 · Pedro Henrique Luz de Araujo, Teófilo Emidio de Campos, Marcelo Magalhães Silva de Sousa

Official Gazettes are a rich source of relevant information to the public. Their careful examination may lead to the detection of frauds and irregularities that may prevent mismanagement of public funds. This paper presents a dataset composed of documents from the Official Gazette of the Federal District, containing both samples with document source annotation and unlabeled ones. We train, evaluate and compare a transfer learning based model that uses ULMFiT with traditional bag-of-words models that use SVM and Naive Bayes as classifiers. We find the SVM to be competitive, its performance being marginally worse than the ULMFiT while having much faster train and inference time and being less computationally expensive. Finally, we conduct ablation analysis to assess the performance impact of the ULMFiT parts.

📄 PDF Abstract BibTeX

Code (1)

peluz/kneedle-exploration

Tasks

Text ClassificationTransfer Learning

Methods 이 논문이 사용한 방법론

Tanh Activation 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Sigmoid Activation 설명 없음
Activation Regularization Activation Regularization (AR), or $L\_{2}$ activation regularization, is regularization performed on activations as opposed to weights. It is usually used in conjunction with…
Temporal Activation Regularization 설명 없음
Weight Tying Weight Tying improves the performance of language models by tying (sharing) the weights of the embedding and softmax layers. This…
LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…
Variational Dropout Variational Dropout is a regularization technique based on dropout, but uses a variational inference grounded approach. In…

Similar Papers 제목 키워드 기반

Low Resource Text Classification with ULMFit and Backtranslation

2019-03-21 · Sam Shleifer

In computer vision, virtually every state-of-the-art deep learning system is trained with data augmentation. In text classification, however, data augmentation is less widely practiced because it must be performed before…

ClassificationData AugmentationGeneral Classificationtext-classification+1

HinglishNLP: Fine-tuned Language Models for Hinglish Sentiment Detection

2020-08-22 · Meghana Bhange, Nirant Kasliwal

Sentiment analysis for code-mixed social media text continues to be an under-explored area. This work adds two common approaches: fine-tuning large transformer models and sample efficient methods like ULMFiT. Prior work …

BIG-bench Machine LearningSentiment Analysis

HinglishNLP at SemEval-2020 Task 9: Fine-tuned Language Models for Hinglish Sentiment Detection

2020-12-01 · SEMEVAL 2020 · Meghana Bhange, Nirant Kasliwal

Sentiment analysis for code-mixed social media text continues to be an under-explored area. This work adds two common approaches: fine-tuning large transformer models and sample efficient methods like ULMFiT. Prior work …

Sentiment Analysis

Inferring about fraudulent collusion risk on Brazilian public works contracts in official texts using a Bi-LSTM approach

2020-11-01 · Findings of the Association for Computational Linguistics 2020 · Marcos Lima, Roberta Silva, Felipe Lopes de Souza Mendes, Leonardo R. de Carvalho 외

Public works procurements move US{\$} 10 billion yearly in Brazil and are a preferred field for collusion and fraud. Federal Police and audit agencies investigate collusion (bid-rigging), over-pricing, and delivery fraud…

Fraud Detection

Towards Offensive Language Identification for Tamil Code-Mixed YouTube Comments and Posts

2021-08-24 · Charangan Vasantharajan, Uthayasanker Thayasivam

Offensive Language detection in social media platforms has been an active field of research over the past years. In non-native English spoken countries, social media users mostly use a code-mixed form of text in their po…

Language IdentificationTransfer LearningTranslationTransliteration