Search (2 results, page 1 of 1)

  • × author_ss:"Zhou, L."
  • × theme_ss:"Computerlinguistik"
  1. Tao, J.; Zhou, L.; Hickey, K.: Making sense of the black-boxes : toward interpretable text classification using deep learning models (2023) 0.01 
    0.005311759 = product of:
  0.037182312 = sum of:
    0.032137483 = weight(_text_:wide in 990) [ClassicSimilarity], result of:
      0.032137483 = score(doc=990,freq=2.0), product of:
        0.1312982 = queryWeight, product of:
          4.4307585 = idf(docFreq=1430, maxDocs=44218)
          0.029633347 = queryNorm
        0.24476713 = fieldWeight in 990, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          4.4307585 = idf(docFreq=1430, maxDocs=44218)
          0.0390625 = fieldNorm(doc=990)
    0.0050448296 = weight(_text_:information in 990) [ClassicSimilarity], result of:
      0.0050448296 = score(doc=990,freq=2.0), product of:
        0.052020688 = queryWeight, product of:
          1.7554779 = idf(docFreq=20772, maxDocs=44218)
          0.029633347 = queryNorm
        0.09697737 = fieldWeight in 990, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          1.7554779 = idf(docFreq=20772, maxDocs=44218)
          0.0390625 = fieldNorm(doc=990)
  0.14285715 = coord(2/14)
    Abstract
    Text classification is a common task in data science. Despite the superior performances of deep learning based models in various text classification tasks, their black-box nature poses significant challenges for wide adoption. The knowledge-to-action framework emphasizes several principles concerning the application and use of knowledge, such as ease-of-use, customization, and feedback. With the guidance of the above principles and the properties of interpretable machine learning, we identify the design requirements for and propose an interpretable deep learning (IDeL) based framework for text classification models. IDeL comprises three main components: feature penetration, instance aggregation, and feature perturbation. We evaluate our implementation of the framework with two distinct case studies: fake news detection and social question categorization. The experiment results provide evidence for the efficacy of IDeL components in enhancing the interpretability of text classification models. Moreover, the findings are generalizable across binary and multi-label, multi-class classification problems. The proposed IDeL framework introduce a unique iField perspective for building trusted models in data science by improving the transparency and access to advanced black-box models.
    Source
    Journal of the Association for Information Science and Technology. 74(2023) no.6, S.685-700
  2. Zhou, L.; Zhang, D.: NLPIR: a theoretical framework for applying Natural Language Processing to information retrieval (2003) 0.01 
    0.005129378 = product of:
  0.035905644 = sum of:
    0.0104854815 = weight(_text_:information in 5148) [ClassicSimilarity], result of:
      0.0104854815 = score(doc=5148,freq=6.0), product of:
        0.052020688 = queryWeight, product of:
          1.7554779 = idf(docFreq=20772, maxDocs=44218)
          0.029633347 = queryNorm
        0.20156369 = fieldWeight in 5148, product of:
          2.4494898 = tf(freq=6.0), with freq of:
            6.0 = termFreq=6.0
          1.7554779 = idf(docFreq=20772, maxDocs=44218)
          0.046875 = fieldNorm(doc=5148)
    0.025420163 = weight(_text_:retrieval in 5148) [ClassicSimilarity], result of:
      0.025420163 = score(doc=5148,freq=4.0), product of:
        0.08963835 = queryWeight, product of:
          3.024915 = idf(docFreq=5836, maxDocs=44218)
          0.029633347 = queryNorm
        0.2835858 = fieldWeight in 5148, product of:
          2.0 = tf(freq=4.0), with freq of:
            4.0 = termFreq=4.0
          3.024915 = idf(docFreq=5836, maxDocs=44218)
          0.046875 = fieldNorm(doc=5148)
  0.14285715 = coord(2/14)
    Abstract
    Zhou and Zhang believe that for the potential of natural language processing NLP to be reached in information retrieval a framework for guiding the effort should be in place. They provide a graphic model that identifies different levels of natural language processing effort during the query, document matching process. A direct matching approach uses little NLP, an expansion approach with thesauri, little more, but an extraction approach will often use a variety of NLP techniques, as well as statistical methods. A transformation approach which creates intermediate representations of documents and queries is a step higher in NLP usage, and a uniform approach, which relies on a body of knowledge beyond that of the documents and queries to provide inference and sense making prior to matching would require a maximum NPL effort.
    Source
    Journal of the American Society for Information Science and technology. 54(2003) no.2, S.115-123

Authors

Years