added mobilebert notebook

Author: cocoa-xu

notebooks/mobilebert.livemd

@@ -0,0 +1,109 @@
+# BERT Question and Answer
+
+```elixir
+Mix.install([
+  {:tflite_elixir, "~> 0.3.1"},
+  {:req, "~> 0.3.0"},
+  {:kino, "~> 0.9.0"}
+])
+```
+
+## How it works
+
+The model can be used to build a system that can answer users’ questions in natural language. It was created using a pre-trained BERT model fine-tuned on SQuAD 1.1 dataset.
+
+[BERT](https://github.com/google-research/bert), or Bidirectional Encoder Representations from Transformers, is a method of pre-training language representations which obtains state-of-the-art results on a wide array of Natural Language Processing tasks.
+
+This app uses a compressed version of BERT, MobileBERT, that runs 4x faster and has 4x smaller model size.
+
+[SQuAD](https://rajpurkar.github.io/SQuAD-explorer/), or Stanford Question Answering Dataset, is a reading comprehension dataset consisting of articles from Wikipedia and a set of question-answer pairs for each article.
+
+The model takes a passage and a question as input, then returns a segment of the passage that most likely answers the question. It requires semi-complex pre-processing including tokenization and post-processing steps that are described in the BERT [paper](https://arxiv.org/abs/1810.04805) and implemented in the sample app.
+
+```elixir
+alias TFLiteElixir.MobileBert
+```
+
+## Download model
+
+Download the pre-trained TensorFlow Lite MobileBert model.
+
+```elixir
+# /data is the writable portion of a Nerves system
+downloads_dir =
+  if Code.ensure_loaded?(Nerves.Runtime), do: "/data/livebook", else: System.tmp_dir!()
+
+download = fn url, save_as ->
+  save_as = Path.join(downloads_dir, save_as)
+  unless File.exists?(save_as), do: Req.get!(url, output: save_as)
+  save_as
+end
+
+data_files =
+  [
+    mobiler_bert: {
+        "https://tfhub.dev/tensorflow/lite-model/mobilebert/1/metadata/1?lite-format=tflite",
+        "mobilebert.tflite"
+    },
+  ]
+  |> Enum.map(fn {key, {url, save_as}} -> {key, download.(url, save_as)} end)
+  |> Map.new()
+
+data_files
+|> Enum.map(fn {k, v} -> [name: k, location: v] end)
+|> Kino.DataTable.new(name: "Data files")
+```
+
+## Load MobileBert
+
+```elixir
+alias TFLiteElixir.MobileBert
+{:ok, bert} = MobileBert.init(data_files.mobile_bert)
+```
+
+## Example
+
+Passage (Input)
+
+```elixir
+content = """
+Google LLC is an American multinational technology company 
+that specializes in Internet-related services and products, 
+which include online advertising technologies, search engine, 
+cloud computing, software, and hardware. It is considered one 
+of the Big Four technology companies, alongside Amazon, Apple, 
+and Facebook.
+
+Google was founded in September 1998 by Larry Page and Sergey 
+Brin while they were Ph.D. students at Stanford University in
+California. Together they own about 14 percent of its shares
+and control 56 percent of the stockholder voting power through
+supervoting stock. They incorporated Google as a California
+privately held company on September 4, 1998, in California.
+Google was then reincorporated in Delaware on October 22, 2002.
+An initial public offering (IPO) took place on August 19, 2004,
+and Google moved to its headquarters in Mountain View, California,
+nicknamed the Googleplex. In August 2015, Google announced plans
+to reorganize its various interests as a conglomerate called
+Alphabet Inc. Google is Alphabet's leading subsidiary and will
+continue to be the umbrella company for Alphabet's Internet
+interests. Sundar Pichai was appointed CEO of Google, replacing
+Larry Page who became the CEO of Alphabet.
+"""
+
+:ok
+```
+
+Question (Input)
+
+```elixir
+query = "Who is the CEO of Google?"
+```
+
+Answer (Output)
+
+```elixir
+MobileBert.run(bert, query, content)
+|> Enum.map(fn {score, answer} -> [score: Float.round(score, 6), answer: answer] end)
+|> Kino.DataTable.new(name: "Answer")
+```