Data Conference Databasea Query.Farm index
Speakers

Sujit Pal

Employers on the program

  1. 2023Elsevier Health1 talk
  2. 2022RELX1 talk
  3. 2019Elsevier1 talk
Events3
Conferences2
Talks3
Years active2019–2023
Miles between events2,2223 in-person events · 1 country

Appearances by year

201920202021202220232024202520262027
  • Haystack
  • PyData

Talks

DateEventConferenceRoleTitleLinks
Apr 25, 2023Haystack US 2023HaystackspeakerA Cheap Trick for Semantic Question Answering for the GPU challenged
as Elsevier Health
The ability to handle long question style queries is often de rigueur for modern search engines. Search giants such as Bing and Google are addressing this by…Show less

The ability to handle long question style queries is often de rigueur for modern search engines. Search giants such as Bing and Google are addressing this by building Large Language Models (LLMs) into their search pipelines.

SlidesVideo
Apr 27, 2022Haystack US 2022HaystackspeakerLearning a Joint Embedding Representation for Image Search using Self Supervised Means
as RELX Group
Image search interfaces either prompt the searcher to provide a search image (image-to-image search) or a text description of the image (text-to-image search).…Show less

Image search interfaces either prompt the searcher to provide a search image (image-to-image search) or a text description of the image (text-to-image search). Image to Image search is generally implemented as a nearest neighbor search in a dense image embedding space, where the embedding is derived from Neural Networks pre-trained on a large image corpus such as ImageNet.

SlidesVideo
Dec 3, 2019PyData Los Angeles 2019PyDataspeakerBuilding Named Entity Recognition Models Efficiently using NERDS
as Elsevier Labs
Named Entity Recognition (NER) is foundational for many downstream NLP tasks. The Open Source NERDS toolkit provides algorithms that can be used to quickly…Show less

Named Entity Recognition (NER) is foundational for many downstream NLP tasks. The Open Source NERDS toolkit provides algorithms that can be used to quickly build and evaluate NER models from labeled data such as IOB.

Video

Frequent co-speakers

SpeakerShared eventsShared talksLast together
Doug Turnbull2—2023
Lucian Precup2—2023

Speakers with the same name are merged into one entry, so this page may combine more than one person. Affiliations are shown as each conference listed them.