Learning from Few Samples: Lexical Substitution with Word Embeddings for Short Text Classification

Elekes, Abel; Stefano, Antonino Simone Di; Schäler, Martin; Böhm, Klemens; Keller, Matthias

doi:10.1109/jcdl.2019.00025

Cited by 6 publications

(3 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…We use F1-score (micro-averaged (micro) and macroaveraged (macro)) as it has been the most popular metric in the text categorization research [14]. Micro F1-score is harmonic mean of micro precision and micro recall that are defined in (23) and (24), respectively.…”

Section: B Experimental Setup 1) Policiesmentioning

confidence: 99%

See 1 more Smart Citation

Improving Term Weighting Schemes for Short Text Classification in Vector Space Model

2019

View full text Add to dashboard Cite

Short text is one of the predominant forms of communication with unique characteristics such as short length, high sparsity, and lack of shared context and word co-occurrence. These characteristics distinguish short text from general text and make short text classification a challenging task. Term weighting is an important pre-processing step for text classification in the vector space model. In this paper, we propose three modifications to existing state-of-the-art term weighting schemes: ifn-tp-icf, RFR and modOR and a new term weighting scheme: ifn-modRF. We compare the proposed schemes with ten existing unsupervised and supervised schemes using three datasets of informally written short text: a self-labelled dataset of real-world events from Twitter, a Yahoo! questions dataset and a dataset of product reviews. Based on the experimental results using three popular classifiers, we observe that the proposed scheme ifn-modRF achieves the best F1-scores on the Twitter dataset, while the proposed modification modOR is a consistent performer with the best scores in most of the experiments. The proposed modification ifn-tp-icf also outperform the original scheme in most experiments. INDEX TERMS Text classification, text categorization, term weighting, twitter.

show abstract

Section: B Experimental Setup 1) Policiesmentioning

confidence: 99%

“…Topic modelling techniques Latent Semantic Analysis (LSA) and Latent Dirichlet Allocation (LDA) were used in [18] and [19], respectively. Recently, deep learning based short text classification has become popular (see [23], [24]).…”

Section: Introductionmentioning

confidence: 99%

Improving Term Weighting Schemes for Short Text Classification in Vector Space Model

2019

View full text Add to dashboard Cite

show abstract

“…O autor cita como classificadores de melhor desempenho o Random Forest e a Deep Learning-Based Conventional Network.Um método geral de pré-processamento então foi proposto para cenários em que os dados de treinamento são escassos. Ele agrupa termos semanticamente semelhantes através do Word Embedding, que simulam como humanos pré-processam textos, substituindo palavras desconhecidas por termos conhecidos e também agrupando palavras semanticamente semelhantes(Elekes, Di Stefano, Schaler, Bohm, & Keller, 2019).Neste outro trabalho foram realizados experimentos adicionando técnicas de Word Embedding, usando não só o Word2vec mas também testando o Doc2vec, para um conjunto de classificação de textos clínicos. Os resultados foram comparados com o uso do método tradicional Bag Of Words.…”

unclassified

Utilização Prática De Word Embedding Aplicada À Classificação De Texto

Souza¹,

Gonçalves²,

Souza³

2020

Anais Do X Congresso Internacional De Conhecimento E Inovação (ciKi)

View full text Add to dashboard Cite

Text classification aims to extract knowledge from unstructured text patterns. The concept of word incorporation is a representation technique that allows words with similar meanings to have a similar representation, in order to incorporate reasoning characteristics about their use and meaning. The aim of this article is to analyze the work already published on the use of embedded words applied to the classification of texts, to propose a practical application that demonstrates its effectiveness. This study contributes to proving the effectiveness of the use of word incorporation applied to text classification, having reached an accuracy rate of around 73%.

show abstract