Enregistré dans:
Détails bibliographiques
Auteurs principaux: Goto, Takumi, Nagao, Hiroyoshi, Koreeda, Yuta
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2408.09640
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866916514914893824
author Goto, Takumi
Nagao, Hiroyoshi
Koreeda, Yuta
author_facet Goto, Takumi
Nagao, Hiroyoshi
Koreeda, Yuta
contents Using token representation from bidirectional language models (LMs) such as BERT is still a widely used approach for token-classification tasks. Even though there exist much larger unidirectional LMs such as Llama-2, they are rarely used to replace the token representation of bidirectional LMs. In this work, we hypothesize that their lack of bidirectionality is keeping them behind. To that end, we propose to newly train a small backward LM and concatenate its representations to those of existing LM for downstream tasks. Through experiments in named entity recognition, we demonstrate that introducing backward model improves the benchmark performance more than 10 points. Furthermore, we show that the proposed method is especially effective for rare domains and in few-shot learning settings.
format Preprint
id arxiv_https___arxiv_org_abs_2408_09640
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Acquiring Bidirectionality via Large and Small Language Models
Goto, Takumi
Nagao, Hiroyoshi
Koreeda, Yuta
Computation and Language
Using token representation from bidirectional language models (LMs) such as BERT is still a widely used approach for token-classification tasks. Even though there exist much larger unidirectional LMs such as Llama-2, they are rarely used to replace the token representation of bidirectional LMs. In this work, we hypothesize that their lack of bidirectionality is keeping them behind. To that end, we propose to newly train a small backward LM and concatenate its representations to those of existing LM for downstream tasks. Through experiments in named entity recognition, we demonstrate that introducing backward model improves the benchmark performance more than 10 points. Furthermore, we show that the proposed method is especially effective for rare domains and in few-shot learning settings.
title Acquiring Bidirectionality via Large and Small Language Models
topic Computation and Language
url https://arxiv.org/abs/2408.09640