Papers
arxiv:2210.07468

Transparency Helps Reveal When Language Models Learn Meaning

Published on Oct 14, 2022
Authors:
,
,
,

Abstract

Experiments with synthetic and natural languages indicate that current language models struggle with context-dependent semantics, particularly in referentially opaque contexts.

Many current NLP systems are built from language models trained to optimize unsupervised objectives on large amounts of raw text. Under what conditions might such a procedure acquire meaning? Our systematic experiments with synthetic data reveal that, with languages where all expressions have context-independent denotations (i.e., languages with strong transparency), both autoregressive and masked language models successfully learn to emulate semantic relations between expressions. However, when denotations are changed to be context-dependent with the language otherwise unmodified, this ability degrades. Turning to natural language, our experiments with a specific phenomenon -- referential opacity -- add to the growing body of evidence that current language models do not represent natural language semantics well. We show this failure relates to the context-dependent nature of natural language form-meaning mappings.

Community

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2210.07468
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 1

Datasets citing this paper 1

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2210.07468 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.