add documentation; add the original code source info

README.md

@@ -50,7 +50,7 @@ The following is a summary of the commonly used NLP scenarios covered in the rep
 |-------------------------|  ------------------- |-------|---|
 |Text Classification                     |BERT, XLNet, RoBERTa| Text classification is a supervised learning method of learning and predicting the category or the class of a document given its text content. |English, Hindi, Arabic|
 |Named Entity Recognition                |BERT| Named entity recognition (NER) is the task of classifying words or key phrases of a text into predefined entities of interest. |English|
-|Text Summarization|BERTSum <br> UniLM (s2s-ft)|Text summarization is a language generation task of summarizing the input text into a shorter paragraph of text.|English
+|Text Summarization|BERTSumExt <br> BERTSumAbs <br> UniLM (s2s-ft)|Text summarization is a language generation task of summarizing the input text into a shorter paragraph of text.|English
 |Entailment                              |BERT, XLNet, RoBERTa| Textual entailment is the task of classifying the binary relation between two natural-language texts,  *text* and *hypothesis*, to determine if the *text* agrees with the *hypothesis* or not. |English|
 |Question Answering                      |BiDAF, BERT, XLNet| Question answering (QA) is the task of retrieving or generating a valid answer for a given query in natural language, provided with a passage related to the query. |English|
 |Sentence Similarity                     |BERT, GenSen| Sentence similarity is the process of computing a similarity score given a pair of text documents. |English|

cgmanifest.json

@@ -18,7 +18,18 @@
         }
       },
       "license": "Apache-2.0"
+   },
+   {
+      "component": { 
+      "type": "git", 
+      "git": { 
+        "repositoryUrl": "https://github.com/nlpyang/PreSumm", 
+        "commitHash": "2df3312582a3a014aacbc1be810841705c67d06e" 
+        }
+      },
+      "license": "MIT License"
    }
+
  ],
  "Version": 1
-}
+}

examples/text_summarization/abstractive_summarization_bertsumabs_cnndm.ipynb

@@ -356,7 +356,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "generated_summaries[1]"
+    "generated_summaries[0]"
    ]
   },
   {
@@ -365,7 +365,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "reference_summaries[1]"
+    "reference_summaries[0]"
    ]
   },
   {

utils_nlp/models/transformers/bertsum/adam.py

@@ -1,3 +1,9 @@
+# Copyright (c) Microsoft Corporation.
+# Licensed under the MIT License.
+# This script reuses code from https://github.com/nlpyang/Presumm
+
+""" Implementation of ADAM optimizer. """
+
 import math
 import torch
 from torch.optim.optimizer import Optimizer

utils_nlp/models/transformers/bertsum/beam.py

@@ -1,3 +1,9 @@
+# Copyright (c) Microsoft Corporation.
+# Licensed under the MIT License.
+# This script reuses code from https://github.com/nlpyang/Presumm
+
+""" Beam classes used in the beam search. """
+
 from __future__ import division
 import torch
 from .penalties import PenaltyBuilder

utils_nlp/models/transformers/bertsum/decoder.py

@@ -1,5 +1,9 @@
-"""
-Implementation of "Attention is All You Need"
+# Copyright (c) Microsoft Corporation.
+# Licensed under the MIT License.
+# This script reuses code from https://github.com/nlpyang/Presumm
+
+""" 
+Decoder implementation of "Attention is All You Need"
 """
 
 import torch

utils_nlp/models/transformers/bertsum/encoder.py

@@ -1,3 +1,8 @@
+# Copyright (c) Microsoft Corporation.
+# Licensed under the MIT License.
+# This script reuses code from https://github.com/nlpyang/Presumm
+
+"Encoder classes used in the BertSum models."
 import math
 
 import torch

utils_nlp/models/transformers/bertsum/loss.py

@@ -1,3 +1,9 @@
+# Copyright (c) Microsoft Corporation.
+# Licensed under the MIT License.
+# This script reuses code from https://github.com/nlpyang/Presumm
+
+
+
 """
 This file handles the details of the loss function during training.
 

utils_nlp/models/transformers/bertsum/model_builder.py

@@ -1,7 +1,12 @@
+# Copyright (c) Microsoft Corporation.
+# Licensed under the MIT License.
+# This script reuses code from https://github.com/nlpyang/Presumm
+
+"""
+The BertSum models for both extractive and abstractive summarization.
+"""
+
 import sys
-
-# sys.path.insert(0, "/dadendev/PreSumm2/PreSumm/src")
-
 import copy
 
 import torch

utils_nlp/models/transformers/bertsum/neural.py

@@ -1,3 +1,8 @@
+# Copyright (c) Microsoft Corporation.
+# Licensed under the MIT License.
+# This script reuses code from https://github.com/nlpyang/Presumm
+
+
 import math
 
 import torch

utils_nlp/models/transformers/bertsum/optimizers.py

@@ -1,3 +1,8 @@
+# Copyright (c) Microsoft Corporation.
+# Licensed under the MIT License.
+# This script reuses code from https://github.com/nlpyang/Presumm
+
+
 """ Optimizers class """
 import torch
 import torch.optim as optim

utils_nlp/models/transformers/bertsum/penalties.py

@@ -1,3 +1,9 @@
+# Copyright (c) Microsoft Corporation.
+# Licensed under the MIT License.
+# This script reuses code from https://github.com/nlpyang/Presumm
+
+""" PenaltyBuilder Class used in prediction/translation """
+
 from __future__ import division
 import torch
 

utils_nlp/models/transformers/bertsum/predictor.py

@@ -1,4 +1,7 @@
-#!/usr/bin/env python
+# Copyright (c) Microsoft Corporation.
+# Licensed under the MIT License.
+# This script reuses code from https://github.com/nlpyang/Presumm
+
 """ Translator Class and builder """
 from __future__ import print_function
 import codecs