diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/CountVectorizer.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/CountVectorizer.scala
index f7d08b39a9746ace0a2103d235ad9eb65f10be23..a3845d39777a45ce631fc20e74aa848f9d10d208 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/CountVectorizer.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/CountVectorizer.scala
@@ -206,6 +206,27 @@ class CountVectorizerModel(override val uid: String, val vocabulary: Array[Strin
   /** @group setParam */
   def setMinTF(value: Double): this.type = set(minTF, value)
 
+  /**
+    * Binary toggle to control the output vector values.
+    * If True, all non zero counts are set to 1. This is useful for discrete probabilistic
+    * models that model binary events rather than integer counts
+    *
+    * Default: false
+    * @group param
+    */
+  val binary: BooleanParam =
+    new BooleanParam(this, "binary", "If True, all non zero counts are set to 1. " +
+      "This is useful for discrete probabilistic models that model binary events rather " +
+      "than integer counts")
+
+  /** @group getParam */
+  def getBinary: Boolean = $(binary)
+
+  /** @group setParam */
+  def setBinary(value: Boolean): this.type = set(binary, value)
+
+  setDefault(binary -> false)
+
   /** Dictionary created from [[vocabulary]] and its indices, broadcast once for [[transform()]] */
   private var broadcastDict: Option[Broadcast[Map[String, Int]]] = None
 
@@ -232,7 +253,13 @@ class CountVectorizerModel(override val uid: String, val vocabulary: Array[Strin
       } else {
         tokenCount * minTf
       }
-      Vectors.sparse(dictBr.value.size, termCounts.filter(_._2 >= effectiveMinTF).toSeq)
+      val effectiveCounts = if ($(binary)) {
+        termCounts.filter(_._2 >= effectiveMinTF).map(p => (p._1, 1.0)).toSeq
+      }
+      else {
+        termCounts.filter(_._2 >= effectiveMinTF).toSeq
+      }
+      Vectors.sparse(dictBr.value.size, effectiveCounts)
     }
     dataset.withColumn($(outputCol), vectorizer(col($(inputCol))))
   }
diff --git a/mllib/src/test/scala/org/apache/spark/ml/feature/CountVectorizerSuite.scala b/mllib/src/test/scala/org/apache/spark/ml/feature/CountVectorizerSuite.scala
index 9c9999017317d93d295011af294e9e8da4fe5f69..04f165c5f1e74f96804008c29e1b3c5e7558a0c9 100644
--- a/mllib/src/test/scala/org/apache/spark/ml/feature/CountVectorizerSuite.scala
+++ b/mllib/src/test/scala/org/apache/spark/ml/feature/CountVectorizerSuite.scala
@@ -157,7 +157,7 @@ class CountVectorizerSuite extends SparkFunSuite with MLlibTestSparkContext
       (3, split("e e e e e"), Vectors.sparse(4, Seq())))
     ).toDF("id", "words", "expected")
 
-    // minTF: count
+    // minTF: set frequency
     val cv = new CountVectorizerModel(Array("a", "b", "c", "d"))
       .setInputCol("words")
       .setOutputCol("features")
@@ -168,6 +168,23 @@ class CountVectorizerSuite extends SparkFunSuite with MLlibTestSparkContext
     }
   }
 
+  test("CountVectorizerModel with binary") {
+    val df = sqlContext.createDataFrame(Seq(
+      (0, split("a a a b b c"), Vectors.sparse(4, Seq((0, 1.0), (1, 1.0), (2, 1.0)))),
+      (1, split("c c c"), Vectors.sparse(4, Seq((2, 1.0)))),
+      (2, split("a"), Vectors.sparse(4, Seq((0, 1.0))))
+    )).toDF("id", "words", "expected")
+
+    val cv = new CountVectorizerModel(Array("a", "b", "c", "d"))
+      .setInputCol("words")
+      .setOutputCol("features")
+      .setBinary(true)
+    cv.transform(df).select("features", "expected").collect().foreach {
+      case Row(features: Vector, expected: Vector) =>
+        assert(features ~== expected absTol 1e-14)
+    }
+  }
+
   test("CountVectorizer read/write") {
     val t = new CountVectorizer()
       .setInputCol("myInputCol")