HBMP is a hierarchy-like structure of [BiLSTM](https://paperswithcode.com/method/bilstm) layers with [max pooling](https://paperswithcode.com/method/max-pooling). All in all, this model improves the previous state of the art for SciTail and achieves strong results for the SNLI and MultiNLI.

**Population Based Training**, or **PBT**, is an optimization method for finding parameters and hyperparameters, and extends upon parallel search methods and sequential optimisation methods.
It leverages information sharing across a population of concurrently running optimisation processes, and allows for online propagation/transfer of parameters and hyperparameters between members of the population based on their performance. Furthermore, unlike most other adaptation schemes, the method is capable of performing online adaptation of hyperparameters -- which can be particularly important in problems with highly non-stationary learning dynamics, such as reinforcement learning settings. PBT is decentralised and asynchronous, although it could also be executed semi-serially or with partial synchrony if there is a binding budget constraint.

Population Based Training

Population Based Training of Neural Networks

HBMP

Sentence Embeddings in NLI with Iterative Refinement Encoders

SAFRAN is a rule application framework which aggregates rules through a scalable clustering algorithm.

Source	Sentence Embeddings in NLI with Iterative Refinement Encoders
Year	2000
Data Source	CC BY-SA - https://paperswithcode.com