Knowledge about an organization’s products, processes, and services is often buried within terse and bulky knowledge repositories. The ability to bring out the required information efficiently, quickly and reliably to the relevant members of the organization goes a long way in improving efficiency and productivity thereby reducing costs. Keyword-based search solutions return a list of documents ranked by relevance, and the user has to read one or more documents to get an answer to the query.

This session presents an introduction to deep-learning based question-answer models. By virtue of the underlying transfer learning layer (using contextualized word embeddings such as BERT) off the shelf, question-answer models can easily find exact answers to factoid questions without the need for any training. End-users of an organization’s products often require support on procedures for different tasks. The talk presents the latest models in goal-oriented messaging that can be used to query the steps required to execute a task.

Word embeddings are the plinth stones of Natural Language Processing (NLP) applications, used to transform human language into vectors that can be understood and processed by machine learning algorithms. Pre-trained word embeddings enable transfer of prior knowledge about the human language into a new application thereby enabling rapid creation of a scalable and efficient NLP applications. Since the emergence of word2vec in 2013, the word embeddings field has seen rapid developments by leaps and bounds with each new successive word embedding outperforming the prior one.

The goal of this talk is to demonstrate the efficacy of using pre-trained word embedding to create scalable and robust NLP applications, and to explain to the audience the underlying theory of word embeddings that makes it possible. The talk will cover prominent word vector embeddings such as BERT and ELMo from the recent literature.

The desire to reduce the cognitive load on human agents for processing swathes of data in natural languages is driving the adoption of machine learning based software solutions for extracting structured information from unstructured text for a variety of use case scenarios such as monitoring Internet sites for potential terror threat and analyzing documents from disparate sources to identify potentially illegal transactions. These aforementioned software solutions for extracting structured information from unstructured text rely on the ability to identify the entities and the relationship between the entities using Natural Language Processing that has benefitted immensely from the progress in deep learning.

The goal of this talk is to introduce relationship extraction a key plinth stone of natural language understanding, and its use for building knowledge graphs to represent structured information extracted from unstructured text. The talk demonstrates how deep learning lends itself well to the problem of relationship extraction and provides an elegant and simple solution.