.png){kind=icon}
返回
Do Language Models' Words Refer?
.png){kind=icon}
OA
AI
DOI：10.1162/coli_a_00522.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
What do language models (LMs) do with language? They can produce sequences of (mostly) coherent strings closely resembling English. But do those sentences mean something, or are LMs simply babbling in a convincing simulacrum of language use? We address one aspect of this broad question: whether LMs' words can refer, that is, achieve word-to-world connections. There is prima facie reason to think they do not, since LMs do not interact with the world in the way that ordinary language users do. Drawing on the externalist tradition in philosophy of language, we argue that those appearances are misleading: Even if the inputs to LMs are simply strings of text, they are strings of text with natural histories, and that may suffice for LMs' words to refer.
期刊
IF:
5.3
论文数:
837
被引数:
2.7K
机构
引用论文
Let's Play Mono-Poly: BERT Can Reveal Words' Polysemy Level and Partitionability into Senses让我们玩mono-poly: BERT可以将单词的多义性水平和可分割性揭示为感官OAAI
OAAI分享收藏The use of monoamine oxidase inhibition to estimate megakaryocyte-platelet regeneration time (MPRT)
PREAI
分享收藏Outcome of Patients with Acute Myeloid Leukemia Following Failure of Front-Line Venetoclax Plus Hypomethylating Agent Therapy.png)
BloodOAAI
BloodIF0
OAAI分享收藏
查看更多内容