Jul 17, 2019 · post

New research: transfer learning for natural language processing

We discussed this research as part of our virtual event on Wednesday, July 24th; you can watch the replay here!

Machine learning powers systems that can translate language, guide searches, and interact with humans.

All around us we are seeing automated systems that are getting better and better at processing natural language. Machines that can work directly with natural language are powerful, especially as a human interface, because language is the most direct way in which we communicate. The potential impact of such systems is immense.

But systems that can do useful things with language must be intelligent - natural language is extremely complex, after all. Increasingly, machine learning algorithms are used to build this type of intelligence by allowing machines to automatically learn patterns of language.

Building machine learning systems ranges from extremely simple to extremely complex. Consider a system that identifies fraudulent credit card transactions.

Many datasets can be represented neatly as a table. There are many useful statistical models that can find patterns in these datasets.

Teaching a machine to learn patterns of fraud is relatively simple. Given a large dataset of information about each transaction and a label indicating that the transaction was or was not fraudulent, there is no shortage of statistical methods that can identify patterns of fraud.

Natural language data is not so simple. It is, at its core, an ordered but idiosyncratic collection of symbols (characters, words, and punctuation). It can be long or short, and it could contain obscure references or slang. It is unstructured, and rarely meaningful in isolation. Meanings are often unstated, or only make sense in a larger context. Systems that process natural language must thus take these properties into account.

Much of the recent work in machine learning for NLP involves building sequence models that can take this sequential and contextual nature of language into account. With deep learning techniques we can build powerful sequence models that can automatically answer questions, translate between languages, detect emotion, and even generate human-like language.

A cutting edge machine learning model can generate human-like text. From

Building these models, however, is expensive, complex, and requires massive datasets. The skills, budget, and data needed are out of reach for most organizations. These deep learning techniques, by themselves, often aren’t practical.

Transfer learning, a method for training models that incorporates knowledge re-use, solves these problems. Neither transfer learning nor sequence models are new technologies, but combining them provides new capabilities. With transfer learning for NLP, you no longer need the resources of a research lab or a Fortune 500 company to build cutting edge NLP products.

The latest report prototype from Cloudera Fast Forward Labs explores transfer learning for natural language processing and its implications. The prototype, which provides state-of-the-art sentiment analysis, was built with a small dataset of just 200 examples on an infrastructure budget of less than $25. With transfer learning, anyone can build state-of-the-art NLP systems without large datasets, trained experts, or expensive infrastructure.

Read more

Jul 22, 2019 · featured post
Jul 8, 2019 · post

Latest posts

Sep 22, 2021 · post

Automatic Summarization from TextRank to Transformers

by Melanie Beck · Automatic summarization is a task in which a machine distills a large amount of data into a subset (the summary) that retains the most relevant and important information from the whole. While traditionally applied to text, automatic summarization can include other formats such as images or audio. In this article we’ll cover the main approaches to automatic text summarization, talk about what makes for a good summary, and introduce Summarize. – a summarization prototype we built that showcases several automatic summarization techniques. more
Sep 21, 2021 · post

Extractive Summarization with Sentence-BERT

by Victor Dibia · In extractive summarization, the task is to identify a subset of text (e.g., sentences) from a document that can then be assembled into a summary. Overall, we can treat extractive summarization as a recommendation problem. That is, given a query, recommend a set of sentences that are relevant. The query here is the document, relevance is a measure of whether a given sentence belongs in the document summary. How we go about obtaining this measure of relevance varies (a common dilemma for any recommendation system). more
Sep 20, 2021 · post

How (and when) to enable early stopping for Gensim's Word2Vec

by Melanie Beck · The Gensim library is a staple of the NLP stack. While it primarily focuses on topic modeling and similarity for documents, it also supports several word embedding algorithms, including what is likely the best-known implementation of Word2Vec. Word embedding models like Word2Vec use unlabeled data to learn vector representations for each token in a corpus. These embeddings can then be used as features in myriad downstream tasks such as classification, clustering, or recommendation systems. more
Jul 7, 2021 · post

Exploring Multi-Objective Hyperparameter Optimization

By Chris and Melanie. The machine learning life cycle is more than data + model = API. We know there is a wealth of subtlety and finesse involved in data cleaning and feature engineering. In the same vein, there is more to model-building than feeding data in and reading off a prediction. ML model building requires thoughtfulness both in terms of which metric to optimize for a given problem, and how best to optimize your model for that metric! more
Jun 9, 2021 ·

Deep Metric Learning for Signature Verification

By Victor and Andrew. TLDR; This post provides an overview of metric learning loss functions (constrastive, triplet, quadruplet, and group loss), and results from applying contrastive and triplet loss to the task of signature verification. A complete list of the posts in this series is outlined below: Pretrained Models as Baselines for Signature Verification -- Part 1: Deep Learning for Automatic Offline Signature Verification: An Introduction Part 2: Pretrained Models as Baselines for Signature Verification Part 3: Deep Metric Learning for Signature Verification In our previous blog post, we discussed how pretrained models can serve as strong baselines for the task of signature verification. more
May 27, 2021 · post

Pretrained Models as a Strong Baseline for Automatic Signature Verification

By Victor and Andrew. Figure 1. Baseline approach for automatic signature verification using pretrained models TLDR; This post describes how pretrained image classification models can be used as strong baselines for the task of signature verification. The full list of posts in the series is outlined below: Pretrained Models as Baselines for Signature Verification -- Part 1: Deep Learning for Automatic Offline Signature Verification: An Introduction Part 2: Pretrained Models as Baselines for Signature Verification Part 3: Deep Metric Learning for Signature Verification As discussed in our introductory blog post, offline signature verification is a biometric verification task that aims to discriminate between genuine and forged samples of handwritten signatures. more

Popular posts

Oct 30, 2019 · newsletter
Exciting Applications of Graph Neural Networks
Nov 14, 2018 · post
Federated learning: distributed machine learning with data locality and privacy
Apr 10, 2018 · post
PyTorch for Recommenders 101
Oct 4, 2017 · post
First Look: Using Three.js for 2D Data Visualization
Aug 22, 2016 · whitepaper
Under the Hood of the Variational Autoencoder (in Prose and Code)
Feb 24, 2016 · post
"Hello world" in Keras (or, Scikit-learn versus Keras)


In-depth guides to specific machine learning capabilities


Machine learning prototypes and interactive notebooks


A usable library for question answering on large datasets.

Explain BERT for Question Answering Models

Tensorflow 2.0 notebook to explain and visualize a HuggingFace BERT for Question Answering model.

NLP for Question Answering

Ongoing posts and code documenting the process of building a question answering model.

Interpretability Revisited: SHAP and LIME

Explore how to use LIME and SHAP for interpretability.


Cloudera Fast Forward is an applied machine learning reseach group.
Cloudera   Blog   Twitter