Improving Language Plasticity via Pretraining with Active Forgetting

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Yihong, Marchisio, Kelly, Raileanu, Roberta, Adelani, David Ifeoluwa, Stenetorp, Pontus, Riedel, Sebastian, Artetxe, Mikel
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929207338074112
author Chen, Yihong
Marchisio, Kelly
Raileanu, Roberta
Adelani, David Ifeoluwa
Stenetorp, Pontus
Riedel, Sebastian
Artetxe, Mikel
author_facet Chen, Yihong
Marchisio, Kelly
Raileanu, Roberta
Adelani, David Ifeoluwa
Stenetorp, Pontus
Riedel, Sebastian
Artetxe, Mikel
contents Pretrained language models (PLMs) are today the primary model for natural language processing. Despite their impressive downstream performance, it can be difficult to apply PLMs to new languages, a barrier to making their capabilities universally accessible. While prior work has shown it possible to address this issue by learning a new embedding layer for the new language, doing so is both data and compute inefficient. We propose to use an active forgetting mechanism during pretraining, as a simple way of creating PLMs that can quickly adapt to new languages. Concretely, by resetting the embedding layer every K updates during pretraining, we encourage the PLM to improve its ability of learning new embeddings within a limited number of updates, similar to a meta-learning effect. Experiments with RoBERTa show that models pretrained with our forgetting mechanism not only demonstrate faster convergence during language adaptation but also outperform standard ones in a low-data regime, particularly for languages that are distant from English.
format Preprint
id arxiv_https___arxiv_org_abs_2307_01163
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Improving Language Plasticity via Pretraining with Active Forgetting
Chen, Yihong
Marchisio, Kelly
Raileanu, Roberta
Adelani, David Ifeoluwa
Stenetorp, Pontus
Riedel, Sebastian
Artetxe, Mikel
Computation and Language
Machine Learning
Neural and Evolutionary Computing
Pretrained language models (PLMs) are today the primary model for natural language processing. Despite their impressive downstream performance, it can be difficult to apply PLMs to new languages, a barrier to making their capabilities universally accessible. While prior work has shown it possible to address this issue by learning a new embedding layer for the new language, doing so is both data and compute inefficient. We propose to use an active forgetting mechanism during pretraining, as a simple way of creating PLMs that can quickly adapt to new languages. Concretely, by resetting the embedding layer every K updates during pretraining, we encourage the PLM to improve its ability of learning new embeddings within a limited number of updates, similar to a meta-learning effect. Experiments with RoBERTa show that models pretrained with our forgetting mechanism not only demonstrate faster convergence during language adaptation but also outperform standard ones in a low-data regime, particularly for languages that are distant from English.
title Improving Language Plasticity via Pretraining with Active Forgetting
topic Computation and Language
Machine Learning
Neural and Evolutionary Computing
url https://arxiv.org/abs/2307.01163