Sveriges mest populära poddar
Data Skeptic
VetenskapTeknologi

seq2seq

22 min•1 mars 2019

A sequence to sequence (or seq2seq) model is neural architecture used for translation (and other tasks) which consists of an encoder and a decoder.

The encoder/decoder architecture has obvious promise for machine translation, and has been successfully applied this way. Encoding an input to a small number of hidden nodes which can effectively be decoded to a matching string requires machine learning to learn an efficient representation of the essence of the strings.

In addition to translation, seq2seq models have been used in a number of other NLP tasks such as summarization and image captioning.

Related Links

Fler avsnitt av Data Skeptic

Visa alla avsnitt av Data Skeptic
Book Ratings and Recommendations
•39 min
Disentanglement and Interpretability in Recommender Systems
•31 min
Collective Altruism in Recommender Systems
•55 min
Niche vs Mainstream
•34 min
Healthy Friction in Job Recommender Systems
•27 min
Fairness in PCA-Based Recommenders
•50 min
Video Recommendations in Industry
•38 min
Eye Tracking in Recommender Systems
•52 min
Cracking the Cold Start Problem
•40 min
Designing Recommender Systems for Digital Humanities
•37 min

Data Skeptic med Kyle Polich finns tillgänglig på flera plattformar. Informationen på denna sida kommer från offentliga podd-flöden.