Search (3 results, page 1 of 1)

  • × author_ss:"Sitbon, L."
  • × year_i:[2010 TO 2020}
  1. Symonds, M.; Bruza, P.; Zuccon, G.; Koopman, B.; Sitbon, L.; Turner, I.: Automatic query expansion : a structural linguistic perspective (2014) 0.00 
    0.0048460825 = product of:
  0.029076494 = sum of:
    0.029076494 = weight(_text_:b in 1338) [ClassicSimilarity], result of:
      0.029076494 = score(doc=1338,freq=2.0), product of:
        0.14855953 = queryWeight, product of:
          3.542962 = idf(docFreq=3476, maxDocs=44218)
          0.041930884 = queryNorm
        0.19572285 = fieldWeight in 1338, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          3.542962 = idf(docFreq=3476, maxDocs=44218)
          0.0390625 = fieldNorm(doc=1338)
  0.16666667 = coord(1/6)
  2. Kholghi, M.; Vine, L.D.; Sitbon, L.; Zuccon, G.; Nguyen, A.: Clinical information extraction using small data : an active learning approach based on sequence representations and word embeddings (2017) 0.00 
    0.0048460825 = product of:
  0.029076494 = sum of:
    0.029076494 = weight(_text_:b in 3920) [ClassicSimilarity], result of:
      0.029076494 = score(doc=3920,freq=2.0), product of:
        0.14855953 = queryWeight, product of:
          3.542962 = idf(docFreq=3476, maxDocs=44218)
          0.041930884 = queryNorm
        0.19572285 = fieldWeight in 3920, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          3.542962 = idf(docFreq=3476, maxDocs=44218)
          0.0390625 = fieldNorm(doc=3920)
  0.16666667 = coord(1/6)
    Abstract
    This article demonstrates the benefits of using sequence representations based on word embeddings to inform the seed selection and sample selection processes in an active learning pipeline for clinical information extraction. Seed selection refers to choosing an initial sample set to label to form an initial learning model. Sample selection refers to selecting informative samples to update the model at each iteration of the active learning process. Compared to supervised machine learning approaches, active learning offers the opportunity to build statistical classifiers with a reduced amount of training samples that require manual annotation. Reducing the manual annotation effort can support automating the clinical information extraction process. This is particularly beneficial in the clinical domain, where manual annotation is a time-consuming and costly task, as it requires extensive labor from clinical experts. Our empirical findings demonstrate that (a) using sequence representations along with the length of sequence for seed selection shows potential towards more effective initial models, and (b) using sequence representations for sample selection leads to significantly lower manual annotation efforts, with up to 3% and 6% fewer tokens and concepts requiring annotation, respectively, compared to state-of-the-art query strategies.
  3. Koopman, B.; Zuccon, G.; Bruza, P.; Sitbon, L.; Lawley, M.: Information retrieval as semantic inference : a graph Inference model applied to medical search (2016) 0.00 
    0.0038768656 = product of:
  0.023261193 = sum of:
    0.023261193 = weight(_text_:b in 3260) [ClassicSimilarity], result of:
      0.023261193 = score(doc=3260,freq=2.0), product of:
        0.14855953 = queryWeight, product of:
          3.542962 = idf(docFreq=3476, maxDocs=44218)
          0.041930884 = queryNorm
        0.15657827 = fieldWeight in 3260, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          3.542962 = idf(docFreq=3476, maxDocs=44218)
          0.03125 = fieldNorm(doc=3260)
  0.16666667 = coord(1/6)

Authors

Themes