Schedule: Text, Language, and Speech sessions

An estimated 80% of data generated is an unstructured format, such as text, an image, audio, or video. Vijay Srinivas Agneeswaran, Pramod Singh, and Akshay Kulkarni explore how to create a language model that generates natural language text by implementing and forming a recurrent neural network and attention networks built on top of TensorFlow 2.0. Read more.

Every day, millions of Vodafone Germany customers reach out through various social media channels about issues related to mobile, internet, signal issues, etc. Adithya Hrushikesh details how to build and deploy an ensemble model to classify 26 (originally 56) complaint classes using machine learning over deep learning. He also touches on the business case, data product development, and GDPR. Read more.

Douglas Calegari details a solution that classifies and routes emails coming into a busy insurance service center. Join in to discover how his team evaluated NLP models, leveraged various techniques to increase classification and entity recognition accuracy, designed a scalable end-to-end machine learning data pipeline, and integrated them into an existing transactional system. Read more.

Abhishek Kumar outlines how to industrialize capsule networks by detailing capsule networks and how capsule networks help handle spatial relationships between objects in an image and how to apply them to text analytics and tasks such as NLU or summarization. Join in to see a scalable, productionizable implementation of capsule networks over KubeFlow. Read more.

More than 50% of all interactions between humans and machines are expected to be speech-based by 2022. The challenge: Every AI interprets human language slightly different. Tobias Martens details current issues in NLP interoperability and uses Chomsky's theory of universal hard-wired grammar to outline a framework to make the human voice in AI universal, accountable, and computable. Read more.

To gain an edge in the markets, quantitative hedge fund managers require automated processing to quickly extract actionable information from unstructured and increasingly nontraditional sources of data. Arun Verma shares NLP, AI, and ML techniques that help extract derived signals that have significant trading alpha or risk premium and lead to profitable trading strategies. Read more.

AI-powered market research is performed by indirect approaches based on sparse and implicit consumer feedback (e.g., social network interactions, web browsing, or online purchases). These approaches are more scalable, authentic, and suitable for real-time consumer insights. Gianmario Spacagna proposes a novel algorithm of audience projection able to provide consumer insights over multiple domains. Read more.

Rajib Biswas outlines the application of AI algorithms like generative adversarial networks (GANs) to solve natural language synthesis tasks. Join in to learn how AI can accomplish complex tasks like machine translation, write poetry with style, read a novel, and answer your questions. Read more.

Danielle Deibler examines an approach to detecting bias, fine-grained emotional sentiment, and misinformation through the detection of political narratives in online media. As building blocks, the methodology uses human-in-the-loop, alongside other natural language processing and computational linguistics techniques, with examples focused on the 2020 US presidential election. Read more.

Many natural language processing (NLP) tasks require each word in the input text to be mapped to a vector of real numbers. Julien Simon explores word vectors, why they’re so important, and which are the most popular algorithms to compute them (Word2Vec, GloVe, BERT). You'll get to see how to solve typical NLP problems through several demos by either computing embeddings or reusing pretrained ones. Read more.

Holger Kyas details the AI multicloud broker, which is triggered by Amazon Alexa and mediates between AWS Comprehend (Amazon), Azure Text Analytics (Microsoft), GCP Natural Language (Google), and Watson Tone Analyzer (IBM) to compare and analyze sentiment. The extended AI part generates new sentences (e.g., marketing slogans) with a recurrent neural network (RNN). Read more.

AI assistants are getting a great deal of attention from the industry and research. However, the majority of assistants built to this day are still developed using a state machine and a set of rules. That doesn’t scale in production. Tyler Dunn explores how to build AI assistants that go beyond FAQ interactions using machine learning and open source tools. Read more.

Natural language processing (NLP) is hard, especially for clinical text. Manas Ranjan Kar explains the multiple challenges of NLP for clinical text and why it's so important that we invest a fair amount of time on domain-specific feature engineering. It’s also crucial to understand to diagnose an NLP model performance and identify possible gaps. Read more.

Weifeng Zhong explores a novel method to learn structural changes embedded in unstructured texts based on the Policy Change Index (PCI) framework developed by economists Julian Chan and Weifeng Zhong. He explains how an off-the-shelf application of deep learning—with an important twist—can help you detect structural break points in time series text data. Read more.

Voiced-based AI continues to gain popularity among customers, businesses, and brands, but it’s important to understand that, while it presents a slew of new data at our disposal, the technology is still in its infancy. Andreas Kaltenbrunner examines three ways voice assistants will make big data analytics more complex and the various steps you can take to manage this in your company. Read more.

Efforts to counter human trafficking internationally must assess data from a variety of sources to determine where best to devote limited resources. Tom Sabo explores text-based machine learning, rule-based text extraction to generate training data for modeling efforts, and interactive visualization to improve international trafficking response. Read more.