Natural Language Processing Track

Workshop | NLP | Beginner-Intermediate

In this session, I’ll start by introducing the recent breakthroughs in NLP that resulted from the combination of Transfer Learning and Transformer architectures. Then, we’ll learn to use the open-source tools released by HuggingFace like the Transformers and Tokenizers libraries and the distilled models.
Learning outcomes: understanding Transfer Learning in NLP, how the Transformers and Tokenizers libraries are organized and how to use them for downstream tasks like text classification, NER and text generation...more details

Workshop

Workshop | NLP | Machine Learning | Intermediate-Advanced

This workshop teaches you the use of transformer neural networks and their incarnations (BERT, RoBERTa, GPT-2) for solving real-world natural language use cases. NLP has advanced tremendously over the last few years and BERT is at the forefront of this success having achieved state-of-the-art results on 11 different NLP tasks. For businesses, BERT has unlocked new NLP use cases that have been previously unattainable.

This workshop will teach you what transformers and systems like BERT and GPT-2 are and how to use and modify them for your needs. Organizations have a wealth of unstructured text sources in every line of business, such as employee feedback in human resources, purchase orders and legal documents in contracting and procurement, communication records throughout the org, and many more. Making sense of this information and organizing it into knowledge and actionable insights to improve business outcomes is a key function every data scientist should be aware of…more details

Talk | Machine Learning | Beginner-Intermediate

So what can we use today? Two related approaches for agent-based learning that exist for real world use cases are Contextual Bandits and Imitation Learning. Both can be seen as simplifications to the full RL problem by relaxing certain assumptions, such as the number of environmental states or the need to balance online exploitation vs exploration, respectively. This talk will introduce both the formal Contextual Bandit and Imitation Learning problems, how they differ from full RL, what their limitations are, and where they can be used to solve real world problems...more details

Talk | NLP | Open-source | Intermediate

Natural language processing has exploded in popularity during the last decade. No longer confined to academia, many companies now see NLP as a critical portion of their business intelligence, with the NLP market size expected to double again in the next two years. Traditional NLP approaches like sentiment analysis and topic modeling provide undeniably meaningful insights, but what other techniques can be leveraged to mine information from text?

This talk focuses on lesser known NLP methods that can help unearth novel observations and make analyses more memorable. After a brief introduction to the topic, attendees will learn about various open-source Python packages they can apply to enhance their NLP workflows. Example use cases will also be discussed to further solidify how each technique may be leveraged with existing data. Attendees of this talk will discover several unconventional NLP tools such as:
– Scattertext for comparing word usage between two populations
– spaCy’s linguistic features to parse sentences by syntax
– DeepMoji for assigning emoji labels to short text…more details

Talk | NLP | ML for Programmers | Intermediate

Machine learning has become a core technology underlying many modern applications, especially utilizing natural language processing, where the techniques provide powerful methods for analyzing large data sets, such as contracts, electronic health records, social interactions, and other unstructured text data. With the ability for recent powerful techniques to retain meaning, search, and perform machine translation at high fidelity, alongside many open source traditional and hybrid methods, transforming unstructured content to structured insights, events, and relationships is at the fingertips. Organizations are looking to leverage these emerging technologies and close capability gaps to ingest, monitor, error-check, automate, or improve their capabilities in processing and understanding hundreds of millions of documents. While certain tasks are well addressed by existing systems, organizations often still struggle with implementation, identification of the correct methods & algorithms, as well as properly scale their models to solve open challenges within their terminology. In this session, we examine the data strategy and technical use cases involving natural language processing, the algorithms appropriate for certain project objectives, and discuss the development and deployment of these solutions…more details

Talk | NLP | Deep Learning | Intermediate

Accelerating progress in personalized healthcare requires learning the causal relationships between diseases, genes, treatments, medications, labs, and other clinical information – at scale over a large population and time range. More than half of the clinically relevant data in oncology is only found in free-text pathology reports, radiology reports, sequencing reports, and progress notes.

Extracting and normalizing these facts from these clinical documents requires training oncology-specific models that can accurately extract these specific facts from a variety of documents. This talk describes results and lessons learned, from a real-world project doing this at scale…more details

Tutorial | NLP | Machine Learning | Intermediate

David Talby presents the open-source Spark NLP package for training distributed custom natural language machine-learned pipelines on Apache Spark. The library natively extends Spark ML and includes state-of-the-art deep learning models, language models, and 30+ pre-trained NLP models. The talk walks through the library’s goals, design and API’s, using Jupyter notebooks that will be made publicly available after the talk. Best practices and industry use cases where the library has been applied will be discussed as well…more details