Home |  English version |  Mappa |  Commenti |  Sondaggio |  Staff |  Contattaci Cerca nel sito  
Istituto di scienza e tecnologie dell'informazione "Alessandro Faedo"

Torna all'elenco Report e working Paper anno 2019

Report e working Paper

Tipo: Rapporto di ricerca (Research report)

Titolo: Word-Class Embeddings for Multiclass Text Classification

Anno di pubblicazione: 2019

Formato: Elettronico

Autori: Moreo Fernandez A.D.; Esuli A.; Sebastiani F.

Affiliazioni autori: CNR-ISTI, Pisa, Italy; CNR-ISTI, Pisa, Italy; CNR-ISTI, Pisa, Italy

Autori CNR:

  • ANDREA ESULI
  • ALEJANDRO DAVID MOREO FERNANDEZ
  • FABRIZIO SEBASTIANI

Lingua: inglese

Sintesi: Pre-trained word embeddings encode general word semantics and lexical regularities of natural language, and have proven useful across many NLP tasks, including word sense disambiguation, machine translation, and sentiment analysis, to name a few. In supervised tasks such as multiclass text classification (the focus of this article) it seems appealing to enhance word representations with ad-hoc embeddings that encode task-specific information. We propose (supervised) word-class embeddings (WCEs), and show that, when concatenated to (unsupervised) pre-trained word embeddings, they substantially facilitate the training of deep-learning models in multiclass classification by topic. We show empirical evidence that WCEs yield a consistent improvement in multiclass classification accuracy, using four popular neural architectures and six widely used and publicly available datasets for multiclass text classification. Our code that implements WCEs is publicly available at this https URL

Lingua sintesi: eng

Pagine da: 1

Pagine a: 29

Pagine totali: 29

Parole chiave:

  • Word-Class Embeddings
  • Word embeddings
  • Distributional hypothesis
  • Multiclass text classification

URL: https://arxiv.org/abs/1911.11506

Strutture CNR:

Moduli:

Allegati: Word-Class Embeddings for Multiclass Text Classification (application/pdf)
preprint OA su arxiv

 
Torna indietro Richiedi modifiche Invia per email Stampa
Home Il CNR  |  I servizi News |   Eventi | Istituti |  Focus