Saved in:
Bibliographic Details
Main Author: Hill, Felix
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2408.03855
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910559663816704
author Hill, Felix
author_facet Hill, Felix
contents Nobody knows how language works, but many theories abound. Transformers are a class of neural networks that process language automatically with more success than alternatives, both those based on neural computations and those that rely on other (e.g. more symbolic) mechanisms. Here, I highlight direct connections between the transformer architecture and certain theoretical perspectives on language. The empirical success of transformers relative to alternative models provides circumstantial evidence that the linguistic approaches that transformers embody should be, at least, evaluated with greater scrutiny by the linguistics community and, at best, considered to be the currently best available theories.
format Preprint
id arxiv_https___arxiv_org_abs_2408_03855
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Why transformers are obviously good models of language
Hill, Felix
Computation and Language
Nobody knows how language works, but many theories abound. Transformers are a class of neural networks that process language automatically with more success than alternatives, both those based on neural computations and those that rely on other (e.g. more symbolic) mechanisms. Here, I highlight direct connections between the transformer architecture and certain theoretical perspectives on language. The empirical success of transformers relative to alternative models provides circumstantial evidence that the linguistic approaches that transformers embody should be, at least, evaluated with greater scrutiny by the linguistics community and, at best, considered to be the currently best available theories.
title Why transformers are obviously good models of language
topic Computation and Language
url https://arxiv.org/abs/2408.03855