jinho features style

ClassifierPos.scala

  def addFeature(v: SparseIndexedTensor1, f: String) { v.update(ClassifierPosFeatureDomain.index(f), 1.0) }
  def addLemma(v: SparseIndexedTensor1, w: WordData, f: String, prefix: String) {
    if (w.ambiguityClasses.contains(f)) addFeature(v, prefix+f)
  }
  def getAffinity(sent: SentenceData, w: WordData, pos: Int) {
    val f = sent.get(sent.lemmas, pos)
    if (w.ambiguityClasses.contains(f)) w.ambiguityClasses(f) else ""
  }
  def getLemmaFeature(sent: SentenceData, w: WordData, pos: Int, dif: Int) = {
    val prefix = "W"+(dif)+"="
    val lemma = sent.get(sent.lemmas, pos+dif)
    if (w.ambiguityClasses.contains(lemma))
      prefix+lemma
    else
      prefix
  }
  def addFeatures(sent: SentenceData, pos: Int, f: SparseIndexedTensor1, w: WordData) {
    val wp3 = getLemmaFeature(sent, w, pos, +3)
    val wp2 = getLemmaFeature(sent, w, pos, +2)
    val wp1 = getLemmaFeature(sent, w, pos, +1)
    val wf = getLemmaFeature(sent, w, pos, 0)
    val wm1 = getLemmaFeature(sent, w, pos, -1)
    val wm2 = getLemmaFeature(sent, w, pos, -2)
    val wm3 = getLemmaFeature(sent, w, pos, -3)

    val pm3 = "POS-3="+sent.get(sent.labels, pos-3)
    val pm2 = "POS-2="+sent.get(sent.labels, pos-2)
    val pm1 = "POS-1="+sent.get(sent.labels, pos-1)
    val a0 = "A="+getAffinity(sent, w, pos)
    val ap1 = "A+1="+getAffinity(sent, w, pos+1)
    val ap2 = "A+2="+getAffinity(sent, w, pos+2)
    val ap3 = "A+3="+getAffinity(sent, w, pos+3)

    addFeature(f, wp3)
    addFeature(f, wp2)
    addFeature(f, wp1)
    addFeature(f, wf)
    addFeature(f, wm1)
    addFeature(f, wm2)
    addFeature(f, wm3)

    addFeature(f, pm3)
    addFeature(f, pm2)
    addFeature(f, pm1)

    addFeature(f, a0)
    addFeature(f, ap1)
    addFeature(f, ap2)
    addFeature(f, ap2)

    addFeature(f, wm2+wm1)
    addFeature(f, wm1+wf)
    addFeature(f, wf+wp1)
    addFeature(f, wp1+wp2)
    addFeature(f, wm1+wp1)

    addFeature(f, pm2+pm1)
    addFeature(f, ap1+ap2)
    addFeature(f, pm1+ap1)
    addFeature(f, pm1+a0)
    addFeature(f, a0+ap1)

    addFeature(f, wm2+wm1+wf)
    addFeature(f, wm1+wf+wp1)
    addFeature(f, wf+wp1+wp2)
    addFeature(f, wm2+wm1+wp1)
    addFeature(f, wm1+wp1+wp2)

    addFeature(f, pm2+pm1+a0)
    addFeature(f, pm1+a0+ap1)
    addFeature(f, pm2+pm1+ap1)
    addFeature(f, pm1+ap1+ap2)
    addFeature(f, a0+ap1+ap2)

    addFeature(f, "PREFX3="+wf.take(3))
    addFeature(f, "SUFX4="+wf.takeRight(4))


    addFeature(f, "Shape="+strings.stringShape(wf, 2)) // TODO(apassos): add the remaining jinho features not contained in shape
    addFeature(f, "HasPeriod="+wf.contains("."))
    addFeature(f, "HasDigit="+wf.contains("0"))
    addFeature(f, "HasHyphen="+wf.contains("-"))
  }