fbpx
Watch: Effective Transfer Learning for NLP
Transfer learning, the practice of applying knowledge gained on one machine learning task to aid the solution of a second task, has seen historic success in the field of computer vision. The output representations of generic image classification models trained on ImageNet have been leveraged to build models that... Read more
Watch: State of the Art Natural Language Understanding at Scale
Natural language understanding is a key component in many data science systems that must understand or reason about text. Common use cases include question answering, paraphrasing or summarization, sentiment analysis, natural language BI, language modeling, and disambiguation. Building such systems usually requires combining three types of software libraries: NLP... Read more
Watch: Understanding Unstructured Data with Language Models
As data scientists, we’ve seen a rapid improvement in the last decades in the tools available for working with structured data (be it tabular data, graph data, sensor data etc.). Yet, the vast majority of our data (Merrill Lynch puts the figure at roughly 90%) is *unstructured*, and lives... Read more
20 Open Datasets for Natural Language Processing
Natural language processing is a significant part of machine learning use cases, but it requires a lot of data and some deftly handled training. In 25 Excellent Machine Learning Open Data Sets, we listed Amazon Reviews and Wikipedia Links for general NLP and the Standford Sentiment Treebank and Twitter... Read more
The Most Exciting Natural Language Processing Research of 2019 So Far
The data revolution isn’t just about numbers, as researchers are teaching machines how to process natural language as data. The evolving capacity that machines have to interpret human speech, whether written or spoken, opens new possibilities for the interactions between computers and people. Below, we have highlighted some of... Read more
Ben Vigoda on the New Era of NLP
Many apps and programs claim to be able to understand you and are at least capable of engaging in superficial interactions. Spend long enough talking to one of these programs, however, and you’ll no doubt see the hallmarks of imperfectly reproduced natural language. That technology has not yet caught... Read more
The Power of Universal Latent Space In Medical Breakthroughs
The cost to develop new medicines has grown tremendously despite our computing and medical advances. Although we have a greater need than ever for massive breakthroughs in medical science, the industry itself is still a slow, highly regimented field. Mason Victors, CTO and CPO for Recursion Pharmaceuticals believes that... Read more
Watch: Project Feels – Deep Text Models for Sentiment Analysis
This video discusses the use of active learning, deep learning, Bayesian inference, and causality in Project Feels. This project, developed by the Data Science Group at the New York Times, sought to predict how likely a given article was to evoke a range of emotions. Thus project crowdsourced data... Read more
Watch: A Breakthrough for Natural Language
Natural language is valuable, but it is complex. With a 1,000 word vocabulary, a 15-word sentence can easily express more than 1e30 (a 1 with 30 zeros) different ideas. Today’s natural language processing is trained to bucket a sentence into one of a few thousand categories–which also means it... Read more
The State of Automatic Text Summarization with NLP
Ideally, NLP will be able to help humans complete tedious text-evaluation tasks, and its potential for use in fields like law and medicine have elicited significant enthusiasm. But where NLP has been applied to processes that do not align with strict mathematical evaluation, which perhaps require judgments of value,... Read more