RougeL metric
RougeL class
keras_nlp.metrics.RougeL(use_stemmer=False, name="rouge-l", **kwargs)
ROUGE-L metric.
This class implements the ROUGE-L variant of the ROUGE metric. The ROUGE-L metric is traditionally used for evaluating summarisation systems. Succinctly put, ROUGE-L is a score based on the length of the longest common subsequence present in the reference text and the hypothesis text.
Note on input shapes:
For y_true and y_pred, this class supports scalar values and batch
inputs of shapes (), (batch_size,) and (batch_size, 1).
Arguments
- use_stemmer: bool. Whether Porter Stemmer should be used to strip word
suffixes to improve matching. Defaults to
False. - dtype: string or tf.dtypes.Dtype. Precision of metric computation. If
not specified, it defaults to
"float32". - name: string. Name of the metric instance.
- **kwargs: Other keyword arguments.
References
Examples
- Python string.
>>> rouge_l = keras_nlp.metrics.RougeL()
>>> y_true = "the tiny little cat was found under the big funny bed"
>>> y_pred = "the cat was under the bed"
>>> rouge_l(y_true, y_pred)["f1_score"]
<tf.Tensor: shape=(), dtype=float32, numpy=0.7058824>
- List inputs. a. Python list.
>>> rouge_l = keras_nlp.metrics.RougeL()
>>> y_true = [
... "the tiny little cat was found under the big funny bed",
... "i really love contributing to KerasNLP",
... ]
>>> y_pred = [
... "the cat was under the bed",
... "i love contributing to KerasNLP",
... ]
>>> rouge_l(y_true, y_pred)["f1_score"]
<tf.Tensor: shape=(), dtype=float32, numpy=0.80748665>
- 2D inputs.
>>> rouge_l = keras_nlp.metrics.RougeL()
>>> y_true = [
... ["the tiny little cat was found under the big funny bed"],
... ["i really love contributing to KerasNLP"],
... ]
>>> y_pred = [
... ["the cat was under the bed"],
... ["i love contributing to KerasNLP"],
... ]
>>> rouge_l(y_true, y_pred)["f1_score"]
<tf.Tensor: shape=(), dtype=float32, numpy=0.80748665>