Bart: update example for #3140 compatibility (#3233)

* Update bart example docs

examples/summarization/bart/README.md

@@ -1,4 +1,4 @@
-### Get the CNN/Daily Mail Data
+### Get the CNN Data
 To be able to reproduce the authors' results on the CNN/Daily Mail dataset you first need to download both CNN and Daily Mail datasets [from Kyunghyun Cho's website](https://cs.nyu.edu/~kcho/DMQA/) (the links next to "Stories") in the same folder. Then uncompress the archives by running:
 
 ```bash
@@ -32,6 +32,7 @@ unzip stanford-corenlp-full-2018-10-05.zip
 cd stanford-corenlp-full-2018-10-05
 export CLASSPATH=stanford-corenlp-3.9.2.jar:stanford-corenlp-3.9.2-models.jar
 ```
+Then run `ptb_tokenize` on `test.target` and your generated hypotheses.
 ### Rouge Setup
 Install `files2rouge` following the instructions at [here](https://github.com/pltrdy/files2rouge).
 I also needed to run `sudo apt-get install libxml-parser-perl`

examples/summarization/bart/evaluate_cnn.py

@@ -27,9 +27,11 @@ def generate_summaries(lns, out_file, batch_size=8, device=DEFAULT_DEVICE):
             attention_mask=dct["attention_mask"].to(device),
             num_beams=4,
             length_penalty=2.0,
-            max_length=140,
-            min_length=55,
+            max_length=142,  # +2 from original because we start at step=1 and stop before max_length
+            min_length=56,  # +1 from original because we start at step=1
             no_repeat_ngram_size=3,
+            early_stopping=True,
+            do_sample=False,
         )
         dec = [tokenizer.decode(g, skip_special_tokens=True, clean_up_tokenization_spaces=False) for g in summaries]
         for hypothesis in dec: