Image Credit: Facebook AI Research

Recent am început un nou buletin informativ axat pe educația AI și are deja peste 50,000 de abonați. TheSequence este un buletin informativ axat pe no-BS (adică fără hype, fără știri etc.), care durează 5 minute pentru a fi citit. Scopul este să vă țină la curent cu proiectele de învățare automată, lucrările de cercetare și conceptele. Vă rugăm să încercați abonându-vă mai jos:

Last year, Facebook AI Research(FAIR) open sourced BlenderBot 1.0, the largest open domain chatbot ever built. BlenderBot is able to engage in a large variety of conversations across nearly any topic while displaying human-like characteristics such as empathy and personable levels of engagement. The first version of BlenderBot was one of the first chatbots to combine empathy, personality and knowledge in a single system.

Săptămâna trecută, the FAIR team open sourced a new version of BlenderBot which includes several key improvements to its predecessor. More specifically, BlenderBot 2.0 incorporates two main innovations relative to the previous version:

1. Improved long term memory capabilities.
2. Ability to search the internet for real time knowledge.

Transformer architectures such as GPT-3 or BERT have revolutionized natural language processing(NLP) systems but they still have marked limitations. Among them, long term memory stands out as one of the major drawback of large transformer models. In general, transformer architectures are only able to build short term memory structures that are highly dependent on the pretrained knowledge. For instance, GPT-3 is super knowledgeable about movies and TV series from a few years ago but is not up to date with current shows.

Image Credit: Facebook AI Research

To address this limitation, BlenderBot 2.0 complements the training knowledge with the ability of triggering internet searches for relevant knowledge that is then persisted in its long-term memory store. Architecturally, BlenderBot 2.0 augments its transformer model with an additional neural network that triggers search queries based on a specific conversational context. BlenderBot then combines with search results with the existing conversational knowledge in order to articulate a final response.

Image Credit: Facebook AI Research

The result of the BlenderBot 2.0 architecture is a chatbot that can combine natural conversations with real time knowledge while also accessing the context from previous conversations. The techniques used in BlenderBot 2.0 can inspire a new generation of conversational systems that adapts transformer architectures to the requirements of real world systems.

 
Original. Repostat cu permisiunea.

Related:

• Facebook lansează una dintre cele mai dure provocări de învățare în consolidare din istorie
• DeepMind dorește să reimagineze unul dintre cele mai importante algoritmi în învățarea automată
• Amazing Low-Code Machine Learning Capabilities with New Ludwig Update