Apr 11, 2016 · announcement

New Tools to Summarize Text


We’re excited to introduce the latest report and prototype from our machine intelligence R&D group! In this iteration, we explore summarization, or neural network techniques for making unstructured text data computable.

Making language computable has been a goal of computer science research for decades. Historically, it has been a challenge to merely collect and store data. But it’s now so cheap to store data that we often have the opposite problem: once we’ve data, how should we analyze it to find meaning and insights?

Many organizations have made good headway processing structured, transactional data for Business Intelligence, but few have extended analytics to compress insights from the emails, news articles, reports, legal documents, and other troves of written documents that make up the lifeblood of organizations. 

But we’re beginning to gain the ability to do remarkable things with unstructured text. Businesses that adopt this technology will see significant advantages. They will find important information faster. They will expand the horizons of how and what they read, gleaning actionable insights from document corpuses too large for humans to process.

Our work addresses multi- and single-document summarization, illustrating the best technical approaches with two prototypes. Our multi-document prototype uses Latent Dirichlet Allocation to map topics and collect key points of view across thousands of Amazon product reviews. 

Our single-document prototype, Brief, uses skip-thoughts and recurrent neural networks to extract the sentences that best represent the key ideas in a longer document. You can see how Brief scores and highlights an article’s most interesting sentences in our public preview

Our report records lessons we learned building our prototype, teaching readers:

  • how different algorithms represent unstructured text quantitatively
  • why recent breakthroughs in deep learning allow us to model meaning 
  • how to build a summarization system and setbacks to avoid 
  • who the key summarization vendors are and what they offer
  • where natural language processing will go in the near future

We’re excited to help our clients identify opportunities to use these capabilities in their businesses, be that to facilitate research on investments, find documents relevant for a legal matter, manage email overload after vacation, or automatically generate tweets. What else do you imagine?


Please [contact us]( if you’d like to learn more about our research or advising services. 

And join us May 24 for an online discussion with New York NLP startup Agolo, where we’ll explain how summarization technology works and how businesses are using it today! 

Read more

Apr 15, 2016 · post
Apr 6, 2016 · guest 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