← Search

Ivan Montero

2 accepted papers

2022

How Much Does Attention Actually Attend? Questioning the Importance of Attention in Pretrained Transformers

EMNLP 2022finding

The attention mechanism is considered the backbone of the widely-used Transformer architecture. It contextualizes the input by computing input-specific attention matrices. We find that this mechanism, while powerful and elegant, is not as important as typically thought for pretrained language models…

2021

Sentence Bottleneck Autoencoders from Transformer Language Models

EMNLP 2021main

Representation learning for text via pretraining a language model on a large corpus has become a standard starting point for building NLP systems. This approach stands in contrast to autoencoders, also trained on raw text, but with the objective of learning to encode each input as a vector that allo…