// our training

Artificial Intelligence in Search Training

In this training, you will learn how to design and implement intelligent natural language search leveraging Open Source software.
You will learn about language modelling, vector-based search and how to integrate it with Apache Lucene/Solr and Elasticsearch.

Public Training sessions

First session

Natural Language Processing

This session explores various tasks in NLP that are useful to improve the quality of your search system and how to integrate them into your search engine, using open source software.
  • Public session no more available
Discover more

Second session

Vector-Based Search and Augmenting the Inverted Index

This session explores approaches in sparse and dense vector retrieval, and you are going to learn how to integrate the power of deep learning techniques with your inverted index.
  • Public session no more available
Discover more

Third session

BERT and Transformers

This session gives you a better understanding of how BERT works and how you can integrate it with your search architecture to improve your relevance.
  • Public session no more available
Discover more

Fourth session

Open Source Approaches

This session explores the state of the art of how this innovative approach is supported by Open Source search engines such as Elasticsearch, Apache Solr, OpenSearch and Vespa.
  • Recorded version available
Discover more
Choose the number of sessions to buy

2 SESSIONS

£ 650,00
Buy the first two sessions of this training
• Natural Language Processing
• Vector-Based Search and Augmenting the Inverted Index

By Purchasing the training You Accept our Training’s Terms and Conditions

3 SESSIONS

£ 850,00
Buy the first three sessions of this training
• Natural Language Processing
• Vector-Based Search and Augmenting the Inverted Index
• BERT and Transformers

By Purchasing the training You Accept our Training’s Terms and Conditions

4 SESSIONS

£ 1000,00
Buy all the sessions of this training
• Natural Language Processing
• Vector-Based Search and Augmenting the Inverted Index
• BERT and Transformers
• Open Source Approaches

By Purchasing the training You Accept our Training’s Terms and Conditions

Private and recorded training

Pre-recorded

coming soon

We are working to provide a pre-recorded version of our bestseller training. If you want to receive an email as soon as we publish it, subscribe to our newsletter.
  • Top expert trainers
  • Q&A by e-mail
  • Certificate of Attendance
subscribe

Private

ask for quote

If you are looking for intensive sessions tailored on your (or your team) experience, then private training is your perfect choice! You can choose between online or live training.
  • In-presence or Online
  • Tailored training
  • Top expert trainers
  • Certificate of Attendance
Contact us

Based on experience with leading companies including

feedback from past students
"The course has certainly generated many interesting ideas, but first we have to fill some gaps.
The positive feedback I had about your professionalism and skills in the areas of information retrieval and AI makes me think that you can definitely be an important partner for the growth and development of our products."
Dario Rigolin
Founder
PREREQUISITES

• Basic understanding of Search Engines and Machine Learning.

WHAT YOU WILL LEARN

• How to integrate natural language processing techniques with your search engine
• How to use pre-trained language models and fine-tune them for your specific use case
• The pros/cons of vector-based search
• How to do that with Apache Lucene/Solr and Elasticsearch

INTENDED AUDIENCE

• Software Engineers
• Data Scientists
• Machine Learning passionates.

// Artificial Intelligence in Search Training

Our Trainers

Alessandro Benedetti

APACHE LUCENE/SOLR COMMITTER
APACHE SOLR PMC MEMBER

Alessandro Benedetti is the founder of Sease Ltd.
Alessandro has been involved from the beginning to the Apache Solr Learning To Rank plugin developments carried over by Bloomberg.
Over the years he has worked in various Learning To Rank projects and solutions including the contribution to Apache Solr of the Interleaving capability.

Anna Ruggero

R&D Search Software Engineer, her focus is on the integration of Information Retrieval systems with advanced Machine Learning, Neural Search models ad Recommender Systems.
She likes to find new solutions that integrate her work as a Search Consultant with the latest academic studies.

Ilaria Petreti

Data Scientist, passionate about the world of Artificial Intelligence. She loves applying Data Mining and Machine Learning techniques to help companies making careful data-driven decisions and increase their efficiency.

Full Program

Natural Language Processing

  • Introduction

  • NLP tasks useful for Search

  • Open Source Libraries Overview

  • Text and Speech Processing(Optical Character Recognition, Speech Recognition, Text to Speech, Tokenization)

  • Morphological Analysis(Stemming/Lemmatization, Part Of Speech Tagging)

  • Syntactic Analysis(Sentence Breaking)

  • Lexical Semantics(Named Entity Recognition and Linking, Sentiment Analysis, Word Sense Disambiguation)

  • Discourse(Coreference Resolution)

  • Implicit Semantic(Topic Segmentation and Recognition)

  • Higher Level Application(Automatic Summarization, Grammatical Error Correction, Machine Translation, Natural Language Understanding)

  • Hands on Exercises

Deep Learning for Search

  • A bit of history (challenges with exact matching, Deep Learning, semantic search)
  • Word Embeddings
  • Hands on Exercises: let’s start generating and using word embeddings
  • BERT and transformers
  • Hands on Exercises: let’s use BERT
  • Model fine-tuning (pairwise learning, Margin-MSE aka DistilBERT)
  • Hands on Exercises: Fine-tuning with pairwise learning
  • Similarity search of dense vectors
  • Hands on Exercises: Perform ANN search
  • Augmenting the inverted index (document expansion and emphasize important terms)
  • Hands on Exercises: performing document expansion

Vector Based Search

 

  • How Open Source Search Engines cover the functionality (Apache Lucene/Solr, Elasticsearch and Vespa)
  • Hands on Exercises: let’s run Vector-based search in Open Source search engines
Query Level
  • Query Intent Classification
  • Hands on Exercises: recognise the user intent with Open Source
  • Zero result queries
  • Hands on Exercises: improvement for zero result queries with Open Source backed techniques
Evaluation & Explainability
  • Measure your progress
  • Explainable artificial intelligence

BE THE SEARCH EXPERT OF TOMORROW

    Feel free to contact us

    Your email address will not be published. Required fields are marked *