Sense representations for Portuguese: experiments with sense embeddings and deep neural language models.

Sense representations have gone beyond word representations like Word2Vec, GloVe and FastText and achieved innovative performance on a wide range of natural language processing tasks. Although very useful in many applications, the traditional approaches for generating word embeddings have a strict d...

Descripción completa

Detalles Bibliográficos
Publicado en:Language Resources & Evaluation Vol. 55; no. 4; pp. 901 - 925
Autores principales: Rodrigues da Silva, Jéssica, Caseli, Helena de M.
Formato: Artículo
Publicado: Springer Nature Dec2021
Materias:
Acceso en línea:Ver este registro en EBSCOhost
fields @attributes:
  recordID: 1
pdfLink:
plink: https://search.ebscohost.com/login.aspx?direct=true&db=hlh&AN=152947514&site=ehost-live
header:
  @attributes:
    shortDbName: hlh
    uiTerm: 152947514
    longDbName: Humanities International Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    jinfo:
      jid:
        1574020X
        179V
      jtl: Language Resources & Evaluation
      issn: 1574020X
      maglogo: N
    pubinfo:
      dt: Dec2021
      vid: 55
      iid: 4
      pid: 237
      pub: Springer Nature
    artinfo:
      ui:
        152947514
        10.1007/s10579-020-09525-1
      ppf: 901
      ppct: 24
      formats:
        fmt:
          – @attributes:
              type: T
          – @attributes:
              type: P
              size: 427KB
      tig:
        atl: Sense representations for Portuguese: experiments with sense embeddings and deep neural language models.
      aug:
        au:
          Rodrigues da Silva, Jéssica
          Caseli, Helena de M.
        affil: Federal University of São Carlos (UFSCar), São Carlos, Brazil
      su:
        Natural language processing
        Ambiguity
        Portuguese language
        Language transfer (Language learning)
      sug:
        subj:
          Natural language processing
          Ambiguity
          Portuguese language
          Language transfer (Language learning)
      keyword:
        Deep neural language models
        Portuguese
        Sense embeddings
        Word embeddings
        Word sense disambiguation
      ab: Sense representations have gone beyond word representations like Word2Vec, GloVe and FastText and achieved innovative performance on a wide range of natural language processing tasks. Although very useful in many applications, the traditional approaches for generating word embeddings have a strict drawback: they produce a single vector representation for a given word ignoring the fact that ambiguous words can assume different meanings. In this paper, we explore unsupervised sense representations which, different from traditional word embeddings, are able to induce different senses of a word by analyzing its contextual semantics in a text. The unsupervised sense representations investigated in this paper are: sense embeddings and deep neural language models. We present the first experiments carried out for generating sense embeddings for Portuguese. Our experiments show that the sense embedding model (Sense2vec) outperformed traditional word embeddings in syntactic and semantic analogies task, proving that the language resource generated here can improve the performance of NLP tasks in Portuguese. We also evaluated the performance of pre-trained deep neural language models (ELMo and BERT) in two transfer learning approaches: feature based and fine-tuning, in the semantic textual similarity task. Our experiments indicate that the fine tuned Multilingual and Portuguese BERT language models were able to achieve better accuracy than the ELMo model and baselines.
      pubtype: Academic Journal
      doctype: Article
      src: R
    language: English
    refInfo:
    copyright:
      @attributes:
        flag: Y
      custom: Language Resources & Evaluation is a copyright of Springer, 2021. All Rights Reserved.
      item: Language Resources & Evaluation
      holder: Springer Nature
      dt:
        @attributes:
          year: 2021
    holdings:
      @attributes:
        islocal: N