Example: Token Classification

Token classification is a natural language understanding task in which a label is assigned to some tokens in a text

Named Entity Recognition (NER) and Part-of-Speech (PoS) tagging are two popular token classification subtasks. NER models could be trained to recognize specific entities in a text, such as dates, individuals, and locations, while PoS tagging would identify which words in a text are verbs, nouns, and punctuation marks.

This guide will walk you through an example of NER model monitoring using spacy. Let's start by creating a dummy model:

import spacy

NER = spacy.load("en_core_web_sm")

And let’s assume this is how our prediction function looks like (maybe it’s part of an http server, for example):

def predict(request_id: str, raw_text: str):
  return {
    entity.text: entity.label_ 
    for entity in NER(raw_text).ents

Each entity will include the text, the embedding, and the prediction as follow:

  • text (raw input) - entity.text

  • embedding - entity.vector

  • prediction - entity.label

Storing your Predictions

The next step would be to store your predictions in a data store, including the embeddings themselves. For more information on storing your predictions, please check out the Storing Your Predictions section.

For example, you could use a Parquet file on S3 or a Postgres table that looks like this:

idraw_text (text)embeddings (embedding)prediction (categorical)timestamp (datetime)


I love cookies and Aporia

[0.77, 0.87, 0.94, ...]


2021-11-20 13:41:00


This restaurant was really bad

[0.97, 0.82, 0.13, ...]


2021-11-20 13:45:00


Hummus is a

type of food

[0.14, 0.55, 0.66, ...]


2021-11-20 13:49:00

To integrate this type of model follow our Quickstart.

Check out the data sources section for more information about how to connect from different data sources.

Schema mapping

This type of model is a multiclass model, with text raw input and a embedding feature.

There are 2 unique types in aporia to help you integrate your NLP model - text, and embedding.

The text should be used with your raw_text column. Note that by default, in the UI every string column will be automatically marked as categorical, but you'll have the option to change it to text for NLP use cases.

The embedding as the name suggested, should be used with your embedding column. Note that by default, in the UI every array column will be automatically marked as array, but you'll have the option to change it to embedding for NLP use cases.

Next steps

  • Create a custom dashboard for your model in Aporia - Drag & drop widgets to show different performance metrics, top drifted features, etc.

  • Visualize NLP drift using Aporia's Embeddings Projector - Use the Embedding Projector widget within the investigation room, to view drift between different datasets in production, using UMAP for dimension reduction.

  • Set up monitors to get notified for ML issues - Including data integrity issues, model performance degradation, and model drift. For example:

    • Make sure the distribution of the different entity labels doesn’t drift across time

    • Make sure the distribution of the embedding vector doesn’t drift across time

Last updated