Summarization Examples: add Bart CNN Evaluation (#3082)

* Rename and improve example

* Add test

* slightly faster test

* style

* This breaks remy prolly

* shorter test string

* no slow

* newdir structure

* New tree

* Style

* shorter

* docs

* clean

* Attempt future import

* more import hax

examples/summarization/bart/README.md

@@ -0,0 +1,45 @@
+### Get the CNN/Daily Mail 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
+tar -xvf cnn_stories.tgz && tar -xvf dailymail_stories.tgz
+```
+this should make a directory called cnn_dm/ with files like `test.source`. 
+To use your own data, copy that files format. Each article to be summarized is on its own line.
+
+### Usage
+To create summaries for each article in dataset, run:
+```bash
+python evaluate_cnn.py <path_to_test.source> cnn_test_summaries.txt
+```
+the default batch size, 8, fits in 16GB GPU memory, but may need to be adjusted to fit your system.
+
+### Where is the code?
+The core model is in `src/transformers/modeling_bart.py`. This directory only contains examples.
+
+### (WIP) Rouge Scores
+
+### Stanford CoreNLP Setup
+```
+ptb_tokenize () {
+    cat $1 | java edu.stanford.nlp.process.PTBTokenizer -ioFileList -preserveLines > $2
+}
+
+sudo apt install openjdk-8-jre-headless
+sudo apt-get install ant
+wget http://nlp.stanford.edu/software/stanford-corenlp-full-2018-10-05.zip
+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
+```
+### 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`
+
+```python
+from files2rouge import files2rouge
+from files2rouge import settings
+files2rouge.run(<path_to_tokenized_hypo>,
+                <path_to_tokenized_target>,
+               saveto='rouge_output.txt')
+```

examples/summarization/bart/evaluate_cnn.py

@@ -0,0 +1,60 @@
+import argparse
+from pathlib import Path
+
+import torch
+from tqdm import tqdm
+
+from transformers import BartForMaskedLM, BartTokenizer
+
+
+DEFAULT_DEVICE = "cuda" if torch.cuda.is_available() else "cpu"
+
+
+def chunks(lst, n):
+    """Yield successive n-sized chunks from lst."""
+    for i in range(0, len(lst), n):
+        yield lst[i : i + n]
+
+
+def generate_summaries(lns, out_file, batch_size=8, device=DEFAULT_DEVICE):
+    fout = Path(out_file).open("w")
+    model = BartForMaskedLM.from_pretrained("bart-large-cnn", output_past=True,)
+    tokenizer = BartTokenizer.from_pretrained("bart-large")
+    for batch in tqdm(list(chunks(lns, batch_size))):
+        dct = tokenizer.batch_encode_plus(batch, max_length=1024, return_tensors="pt", pad_to_max_length=True)
+        summaries = model.generate(
+            input_ids=dct["input_ids"].to(device),
+            attention_mask=dct["attention_mask"].to(device),
+            num_beams=4,
+            length_penalty=2.0,
+            max_length=140,
+            min_len=55,
+            no_repeat_ngram_size=3,
+        )
+        dec = [tokenizer.decode(g, skip_special_tokens=True, clean_up_tokenization_spaces=False) for g in summaries]
+        for hypothesis in dec:
+            fout.write(hypothesis + "\n")
+            fout.flush()
+
+
+def _run_generate():
+    parser = argparse.ArgumentParser()
+    parser.add_argument(
+        "source_path", type=str, help="like cnn_dm/test.source",
+    )
+    parser.add_argument(
+        "output_path", type=str, help="where to save summaries",
+    )
+    parser.add_argument(
+        "--device", type=str, required=False, default=DEFAULT_DEVICE, help="cuda, cuda:1, cpu etc.",
+    )
+    parser.add_argument(
+        "--bs", type=int, default=8, required=False, help="batch size: how many to summarize at a time",
+    )
+    args = parser.parse_args()
+    lns = [" " + x.rstrip() for x in open(args.source_path).readlines()]
+    generate_summaries(lns, args.output_path, batch_size=args.bs, device=args.device)
+
+
+if __name__ == "__main__":
+    _run_generate()

examples/summarization/bart/test_bart_examples.py

@@ -0,0 +1,28 @@
+import logging
+import sys
+import tempfile
+import unittest
+from pathlib import Path
+from unittest.mock import patch
+
+from .evaluate_cnn import _run_generate
+
+
+articles = [" New York (CNN)When Liana Barrientos was 23 years old, she got married in Westchester County."]
+
+logging.basicConfig(level=logging.DEBUG)
+
+logger = logging.getLogger()
+
+
+class TestBartExamples(unittest.TestCase):
+    def test_bart_cnn_cli(self):
+        stream_handler = logging.StreamHandler(sys.stdout)
+        logger.addHandler(stream_handler)
+        tmp = Path(tempfile.gettempdir()) / "utest_generations.hypo"
+        with tmp.open("w") as f:
+            f.write("\n".join(articles))
+        testargs = ["evaluate_cnn.py", str(tmp), "output.txt"]
+        with patch.object(sys, "argv", testargs):
+            _run_generate()
+            self.assertTrue(Path("output.txt").exists())