NLP course 4

Author: dheerajnbhat

Diff for: Natural Language Processing/Course 4 - Natural Language Processing with attention models/Assignments/Week 1/Assignment 1- Neural Machine Translation.ipynb

@@ -0,0 +1,138 @@
+{
+  "citation": "@article{DBLP:journals/corr/SeeLM17,\n  author    = {Abigail See and\n               Peter J. Liu and\n               Christopher D. Manning},\n  title     = {Get To The Point: Summarization with Pointer-Generator Networks},\n  journal   = {CoRR},\n  volume    = {abs/1704.04368},\n  year      = {2017},\n  url       = {http://arxiv.org/abs/1704.04368},\n  archivePrefix = {arXiv},\n  eprint    = {1704.04368},\n  timestamp = {Mon, 13 Aug 2018 16:46:08 +0200},\n  biburl    = {https://dblp.org/rec/bib/journals/corr/SeeLM17},\n  bibsource = {dblp computer science bibliography, https://dblp.org}\n}\n\n@inproceedings{hermann2015teaching,\n  title={Teaching machines to read and comprehend},\n  author={Hermann, Karl Moritz and Kocisky, Tomas and Grefenstette, Edward and Espeholt, Lasse and Kay, Will and Suleyman, Mustafa and Blunsom, Phil},\n  booktitle={Advances in neural information processing systems},\n  pages={1693--1701},\n  year={2015}\n}",
+  "description": "CNN/DailyMail non-anonymized summarization dataset.\n\nThere are two features:\n  - article: text of news article, used as the document to be summarized\n  - highlights: joined text of highlights with <s> and </s> around each\n    highlight, which is the target summary",
+  "downloadSize": "585439472",
+  "location": {
+    "urls": [
+      "https://github.com/abisee/cnn-dailymail"
+    ]
+  },
+  "name": "cnn_dailymail",
+  "schema": {
+    "feature": [
+      {
+        "name": "article",
+        "type": "BYTES"
+      },
+      {
+        "name": "highlights",
+        "type": "BYTES"
+      }
+    ]
+  },
+  "splits": [
+    {
+      "name": "test",
+      "numBytes": "49879392",
+      "numShards": "10",
+      "shardLengths": [
+        "11490"
+      ],
+      "statistics": {
+        "features": [
+          {
+            "bytesStats": {
+              "commonStats": {
+                "numNonMissing": "11490"
+              }
+            },
+            "name": "article",
+            "type": "BYTES"
+          },
+          {
+            "bytesStats": {
+              "commonStats": {
+                "numNonMissing": "11490"
+              }
+            },
+            "name": "highlights",
+            "type": "BYTES"
+          }
+        ],
+        "numExamples": "11490"
+      }
+    },
+    {
+      "name": "train",
+      "numBytes": "1260529260",
+      "numShards": "100",
+      "shardLengths": [
+        "17945",
+        "17944",
+        "17945",
+        "17944",
+        "17945",
+        "17944",
+        "17945",
+        "17944",
+        "17945",
+        "17945",
+        "17944",
+        "17945",
+        "17944",
+        "17945",
+        "17944",
+        "17945"
+      ],
+      "statistics": {
+        "features": [
+          {
+            "bytesStats": {
+              "commonStats": {
+                "numNonMissing": "287113"
+              }
+            },
+            "name": "article",
+            "type": "BYTES"
+          },
+          {
+            "bytesStats": {
+              "commonStats": {
+                "numNonMissing": "287113"
+              }
+            },
+            "name": "highlights",
+            "type": "BYTES"
+          }
+        ],
+        "numExamples": "287113"
+      }
+    },
+    {
+      "name": "validation",
+      "numBytes": "57678453",
+      "numShards": "10",
+      "shardLengths": [
+        "13368"
+      ],
+      "statistics": {
+        "features": [
+          {
+            "bytesStats": {
+              "commonStats": {
+                "numNonMissing": "13368"
+              }
+            },
+            "name": "article",
+            "type": "BYTES"
+          },
+          {
+            "bytesStats": {
+              "commonStats": {
+                "numNonMissing": "13368"
+              }
+            },
+            "name": "highlights",
+            "type": "BYTES"
+          }
+        ],
+        "numExamples": "13368"
+      }
+    }
+  ],
+  "supervisedKeys": {
+    "input": "article",
+    "output": "highlights"
+  },
+  "version": "3.0.0"
+}

Diff for: Natural Language Processing/Course 4 - Natural Language Processing with attention models/Assignments/Week 1/NMTModel.png

@@ -0,0 +1,19 @@
+https://storage.googleapis.com/tensor2tensor-data/tmp/data/cnn_dailymail/plain_text/3.0.0/cnn_dailymail-test.tfrecord-00000-of-00001
+https://storage.googleapis.com/tensor2tensor-data/tmp/data/cnn_dailymail/plain_text/3.0.0/cnn_dailymail-train.tfrecord-00000-of-00016
+https://storage.googleapis.com/tensor2tensor-data/tmp/data/cnn_dailymail/plain_text/3.0.0/cnn_dailymail-train.tfrecord-00001-of-00016
+https://storage.googleapis.com/tensor2tensor-data/tmp/data/cnn_dailymail/plain_text/3.0.0/cnn_dailymail-train.tfrecord-00002-of-00016
+https://storage.googleapis.com/tensor2tensor-data/tmp/data/cnn_dailymail/plain_text/3.0.0/cnn_dailymail-train.tfrecord-00003-of-00016
+https://storage.googleapis.com/tensor2tensor-data/tmp/data/cnn_dailymail/plain_text/3.0.0/cnn_dailymail-train.tfrecord-00004-of-00016
+https://storage.googleapis.com/tensor2tensor-data/tmp/data/cnn_dailymail/plain_text/3.0.0/cnn_dailymail-train.tfrecord-00005-of-00016
+https://storage.googleapis.com/tensor2tensor-data/tmp/data/cnn_dailymail/plain_text/3.0.0/cnn_dailymail-train.tfrecord-00006-of-00016
+https://storage.googleapis.com/tensor2tensor-data/tmp/data/cnn_dailymail/plain_text/3.0.0/cnn_dailymail-train.tfrecord-00007-of-00016
+https://storage.googleapis.com/tensor2tensor-data/tmp/data/cnn_dailymail/plain_text/3.0.0/cnn_dailymail-train.tfrecord-00008-of-00016
+https://storage.googleapis.com/tensor2tensor-data/tmp/data/cnn_dailymail/plain_text/3.0.0/cnn_dailymail-train.tfrecord-00009-of-00016
+https://storage.googleapis.com/tensor2tensor-data/tmp/data/cnn_dailymail/plain_text/3.0.0/cnn_dailymail-train.tfrecord-00010-of-00016
+https://storage.googleapis.com/tensor2tensor-data/tmp/data/cnn_dailymail/plain_text/3.0.0/cnn_dailymail-train.tfrecord-00011-of-00016
+https://storage.googleapis.com/tensor2tensor-data/tmp/data/cnn_dailymail/plain_text/3.0.0/cnn_dailymail-train.tfrecord-00012-of-00016
+https://storage.googleapis.com/tensor2tensor-data/tmp/data/cnn_dailymail/plain_text/3.0.0/cnn_dailymail-train.tfrecord-00013-of-00016
+https://storage.googleapis.com/tensor2tensor-data/tmp/data/cnn_dailymail/plain_text/3.0.0/cnn_dailymail-train.tfrecord-00014-of-00016
+https://storage.googleapis.com/tensor2tensor-data/tmp/data/cnn_dailymail/plain_text/3.0.0/cnn_dailymail-train.tfrecord-00015-of-00016
+https://storage.googleapis.com/tensor2tensor-data/tmp/data/cnn_dailymail/plain_text/3.0.0/cnn_dailymail-validation.tfrecord-00000-of-00001
+https://storage.googleapis.com/tensor2tensor-data/tmp/data/cnn_dailymail/plain_text/3.0.0/dataset_info.json