Named Entity Recognition with AutoMM - Quick Start
==================================================

Named entity recognition (NER) refers to identifying and categorizing
key information (entities) from unstructured text. An entity can be a
word or a series of words which correspond to categories such as cities,
time expressions, monetary values, facilities, person, organization,
etc. An NER model usually takes as input an unannotated block of text
and output an annotated block of text that highlights the named entities
with predefined categories. For example, given the following sentences,

-  Albert Einstein was born in Germany and is widely acknowledged to be
   one of the greatest physicists.

The model will tell you that “Albert Einstein” is a PERSON and “Germany”
is a LOCATION. In the following, we will introduce how to use AutoMM for
the NER task, including how to prepare your data, how to train your
model, and what you can expect from the model outputs.

Prepare Your Data
-----------------

Like other tasks in AutoMM, all you need to do is to prepare your data
as data tables (i.e., dataframes) which contain a text column and an
annotation column. The text column stores the raw textual data which
contains the entities you want to identify. Correspondingly, the
annotation column stores the label information (e.g., the *category* and
the *start/end* offset in character level) for the entities. AutoMM
requires the *annotation column* to have the following json format
(Note: do not forget to call json.dumps() to convert python objects into
a json string before creating your dataframe).

-  [{“entity_group”: “PERSON”, “start”: 0, “end”: 15}, {“entity_group”:
   “LOCATION”, “start”: 28, “end”: 35}]

where **entity_group** is the category of the entity and **start** is a
character position indicating where the entity begins while **end**
represents the ending position of the enity. To make sure that AutoMM
can recognise your json annotations, it is required to use the exactly
same keys/properties (entity_group, start, end) specified above when
constructing your data. You can annote “Albert Einstein” as a single
entity group or you can also assign each word a label.

If you are already familar with the NER task, you probably have heard
about the
`BIO <https://en.wikipedia.org/wiki/Inside%E2%80%93outside%E2%80%93beginning_(tagging)>`__
(Benginning-Inside-Outside) format. You can adopt this format (which is
not compulsory) to add an *I-prefix* or a *B-prefix* to each tag to
indicate wether the tag is the beginning of the annotated chunk or
inside the chunk. For example, you can annotate “Albert” as “B-PERSON”
because it is the beginning of the name and “Einstein” as “I-PERSON” as
it is inside the PERSON chunk. You do not need to worry about the *O*
tags, an *O* tag indicates that a word belongs to no chunk, as AutoMM
will take care of that automatically.

Now, let’s look at an example dataset. This dataset is converted from
the `MIT movies
corpus <https://groups.csail.mit.edu/sls/downloads/movie/>`__ which
provides annotations on entity groups such as actor, character,
director, genre, song, title, trailer, year, etc.

.. code:: python

    from autogluon.core.utils.loaders import load_pd
    train_data = load_pd.load('https://automl-mm-bench.s3.amazonaws.com/ner/mit-movies/train.csv')
    test_data = load_pd.load('https://automl-mm-bench.s3.amazonaws.com/ner/mit-movies/test.csv')
    train_data.head(5)




.. raw:: html

    <div>
    <style scoped>
        .dataframe tbody tr th:only-of-type {
            vertical-align: middle;
        }
    
        .dataframe tbody tr th {
            vertical-align: top;
        }
    
        .dataframe thead th {
            text-align: right;
        }
    </style>
    <table border="1" class="dataframe">
      <thead>
        <tr style="text-align: right;">
          <th></th>
          <th>text_snippet</th>
          <th>entity_annotations</th>
        </tr>
      </thead>
      <tbody>
        <tr>
          <th>0</th>
          <td>what movies star bruce willis</td>
          <td>[{"entity_group": "B-ACTOR", "start": 17, "end...</td>
        </tr>
        <tr>
          <th>1</th>
          <td>show me films with drew barrymore from the 1980s</td>
          <td>[{"entity_group": "B-ACTOR", "start": 19, "end...</td>
        </tr>
        <tr>
          <th>2</th>
          <td>what movies starred both al pacino and robert ...</td>
          <td>[{"entity_group": "B-ACTOR", "start": 25, "end...</td>
        </tr>
        <tr>
          <th>3</th>
          <td>find me all of the movies that starred harold ...</td>
          <td>[{"entity_group": "B-ACTOR", "start": 39, "end...</td>
        </tr>
        <tr>
          <th>4</th>
          <td>find me a movie with a quote about baseball in it</td>
          <td>[]</td>
        </tr>
      </tbody>
    </table>
    </div>



Let’s print the first row.

.. code:: python

    print(f"text_snippet: {train_data['text_snippet'][0]}")
    print(f"entity_annotations: {train_data['entity_annotations'][0]}")


.. parsed-literal::
    :class: output

    text_snippet: what movies star bruce willis
    entity_annotations: [{"entity_group": "B-ACTOR", "start": 17, "end": 22}, {"entity_group": "I-ACTOR", "start": 23, "end": 29}]


Training
--------

Now, let’s create a predictor for named entity recognition by seting the
*problem_type* to **ner** and specifying the label column. Then we call
predictor.fit() to train the model for five minutes. To achieve
reasonable performance in your applications, you are recommended to set
a longer enough time_limit (e.g., 30/60 minutes). You can also specify
your backbone model and other hyperparameters using the hyperparameters
argument. Here, we save the model to the path “./automm_ner”.

.. code:: python

    from autogluon.multimodal import MultiModalPredictor
    import uuid
    
    label_col = "entity_annotations"
    model_path = f"./tmp/{uuid.uuid4().hex}-automm_ner"
    predictor = MultiModalPredictor(problem_type="ner", label=label_col, path=model_path)
    predictor.fit(
        train_data=train_data,
        time_limit=300, #second
    )


.. parsed-literal::
    :class: output

    Global seed set to 123
    Auto select gpus: [0]
    Using 16bit native Automatic Mixed Precision (AMP)
    GPU available: True (cuda), used: True
    TPU available: False, using: 0 TPU cores
    IPU available: False, using: 0 IPUs
    HPU available: False, using: 0 HPUs
    LOCAL_RANK: 0 - CUDA_VISIBLE_DEVICES: [0]
    
      | Name              | Type              | Params
    --------------------------------------------------------
    0 | model             | HFAutoModelForNER | 108 M 
    1 | validation_metric | Accuracy          | 0     
    2 | loss_func         | CrossEntropyLoss  | 0     
    --------------------------------------------------------
    108 M     Trainable params
    0         Non-trainable params
    108 M     Total params
    216.661   Total estimated model params size (MB)
    Epoch 0, global step 34: 'val_overall_accuracy' reached 0.76670 (best 0.76670), saving model to '/home/ci/autogluon/docs/_build/eval/tutorials/multimodal/text_prediction/tmp/b26e4f117297450ab54a22a7259d6dc1-automm_ner/epoch=0-step=34.ckpt' as top 3
    Time limit reached. Elapsed time is 0:05:00. Signaling Trainer to stop.
    Epoch 0, global step 65: 'val_overall_accuracy' reached 0.91604 (best 0.91604), saving model to '/home/ci/autogluon/docs/_build/eval/tutorials/multimodal/text_prediction/tmp/b26e4f117297450ab54a22a7259d6dc1-automm_ner/epoch=0-step=65.ckpt' as top 3



.. parsed-literal::
    :class: output

    Downloading builder script:   0%|          | 0.00/6.34k [00:00<?, ?B/s]




.. parsed-literal::
    :class: output

    <autogluon.multimodal.predictor.MultiModalPredictor at 0x7f8498359af0>



Evaluation
----------

Evaluation is also straightforward, we use
`seqeval <https://huggingface.co/spaces/evaluate-metric/seqeval>`__ for
NER evaluation and the supported metrics are *overall_recall*,
*overall_precision*, *overall_f1*, *overall_accuracy*. If you are
interested in seeing the performance on a specific entity group, you can
use the entity group name as the evaluation metric with which you will
obtain the performances (precision, recall, f1) on the given entity
group:

.. code:: python

    predictor.evaluate(test_data,  metrics=['overall_recall', "overall_precision", "overall_f1", "actor"])




.. parsed-literal::
    :class: output

    {'overall_recall': 0.826559280764188,
     'overall_precision': 0.7880357142857143,
     'overall_f1': 0.8068379193710578,
     'actor': {'precision': 0.7582534611288605,
      'recall': 0.8768472906403941,
      'f1': 0.8132495716733296,
      'number': 812}}



Prediction
----------

You can easily obtain the predictions given an input sentence by by
calling predictor.predict().

.. code:: python

    sentence = "Game of Thrones is an American fantasy drama television series created by David Benioff"
    predictions = predictor.predict({'text_snippet': [sentence]})
    print('Predicted entities:', predictions[0])
    
    for entity in predictions[0]:
        print(f"Word '{sentence[entity['start']:entity['end']]}' belongs to group: {entity['entity_group']}")


.. parsed-literal::
    :class: output

    Predicted entities: [{'entity_group': 'B-TITLE', 'start': 0, 'end': 4}, {'entity_group': 'I-TITLE', 'start': 5, 'end': 7}, {'entity_group': 'I-TITLE', 'start': 8, 'end': 15}, {'entity_group': 'B-GENRE', 'start': 31, 'end': 38}, {'entity_group': 'I-GENRE', 'start': 39, 'end': 44}, {'entity_group': 'B-DIRECTOR', 'start': 74, 'end': 79}, {'entity_group': 'I-DIRECTOR', 'start': 80, 'end': 87}]
    Word 'Game' belongs to group: B-TITLE
    Word 'of' belongs to group: I-TITLE
    Word 'Thrones' belongs to group: I-TITLE
    Word 'fantasy' belongs to group: B-GENRE
    Word 'drama' belongs to group: I-GENRE
    Word 'David' belongs to group: B-DIRECTOR
    Word 'Benioff' belongs to group: I-DIRECTOR


Visualization
-------------

If you are running the code in a Jupyter notebook, you can also easily
visualize the predictions using the visualize_ner function which will
highlight the named entities and their labels in a text.

.. code:: python

    from autogluon.multimodal.utils import visualize_ner
    visualize_ner(sentence, predictions[0])




.. raw:: html

    <mark style="background-color:#7F0AAC; color:white; border-radius: 1em .1em; padding: .3em;">Game of Thrones          <b style="background-color:white; color:black; font-size:x-small; border-radius: 0.3em .3em; padding: .1em;">TITLE </b>          </mark> is an American <mark style="background-color:#C4AA2F; color:white; border-radius: 1em .1em; padding: .3em;">fantasy drama          <b style="background-color:white; color:black; font-size:x-small; border-radius: 0.3em .3em; padding: .1em;">GENRE </b>          </mark> television series created by <mark style="background-color:#16A675; color:white; border-radius: 1em .1em; padding: .3em;">David Benioff          <b style="background-color:white; color:black; font-size:x-small; border-radius: 0.3em .3em; padding: .1em;">DIRECTOR </b>          </mark>



Reloading and Continuous Training
---------------------------------

The trained predictor is automatically saved and you can easily reload
it using the path. If you are not saftisfied with the current model
performance, you can continue training the loaded model with new data.

.. code:: python

    new_predictor = MultiModalPredictor.load(model_path)
    new_model_path = f"./tmp/{uuid.uuid4().hex}-automm_ner_continue_train"
    new_predictor.fit(train_data, time_limit=60, save_path=new_model_path)
    test_score = new_predictor.evaluate(test_data, metrics=['overall_f1', 'ACTOR'])
    print(test_score)


.. parsed-literal::
    :class: output

    Global seed set to 123
    Auto select gpus: [0]
    Using 16bit native Automatic Mixed Precision (AMP)
    GPU available: True (cuda), used: True
    TPU available: False, using: 0 TPU cores
    IPU available: False, using: 0 IPUs
    HPU available: False, using: 0 HPUs
    LOCAL_RANK: 0 - CUDA_VISIBLE_DEVICES: [0]
    
      | Name              | Type              | Params
    --------------------------------------------------------
    0 | model             | HFAutoModelForNER | 108 M 
    1 | validation_metric | Accuracy          | 0     
    2 | loss_func         | CrossEntropyLoss  | 0     
    --------------------------------------------------------
    108 M     Trainable params
    0         Non-trainable params
    108 M     Total params
    216.661   Total estimated model params size (MB)
    Time limit reached. Elapsed time is 0:01:00. Signaling Trainer to stop.
    Epoch 0, global step 14: 'val_overall_accuracy' reached 0.91998 (best 0.91998), saving model to '/home/ci/autogluon/docs/_build/eval/tutorials/multimodal/text_prediction/tmp/d18437a8d8f24742923b37ff8843670a-automm_ner_continue_train/epoch=0-step=14.ckpt' as top 3


.. parsed-literal::
    :class: output

    {'overall_f1': 0.8099551651569219, 'ACTOR': {'precision': 0.7653806047966631, 'recall': 0.9039408866995073, 'f1': 0.828910220214568, 'number': 812}}


Other Examples
--------------

You may go to `AutoMM
Examples <https://github.com/autogluon/autogluon/tree/master/examples/automm>`__
to explore other examples about AutoMM.

Customization
-------------

To learn how to customize AutoMM, please refer to
:ref:`sec_automm_customization`.