Word meaning in minds and machines

By Brenden M. Lake, Gregory L. Murphy. 2020

149 citations recorded by the source corpus.

Machines have achieved a broad and growing set of linguistic competencies, thanks to recent progress in Natural Language Processing (NLP). Psychologists have shown increasing interest in such models, comparing their output to psychological judgments such as similarity, association, priming, and comprehension, raising the question of whether the models could serve as psychological theories. In this article, we compare how humans and machines represent the meaning of words. We argue that contemporary NLP systems are fairly successful models of human word similarity, but they fall short in many other respects. Current models are too strongly linked to the text-based patterns in large corpora, and too weakly linked to the desires, goals, and beliefs that people express through words. Word meanings must also be grounded in perception and action and be capable of flexible combinations in ways that current systems are not. We discuss promising approaches to grounding NLP systems and argue that they will be more successful, with a more human-like, conceptual basis for word meaning. (PsycInfo Database Record (c) 2021 APA, all rights reserved).

Subfields: Artificial Intelligence, Cultural Studies, Natural Language Processing, Representation & Self-Supervised Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Cultural Studies

In Natural Language Processing

In Representation & Self-Supervised Learning

Citations in the corpus

Imitating Interactive Intelligence (2020, methodology): “Here, we have taken steps to construct a more general programme of AI research that emphasises the holistic integration of perception, goal-directed, embodied control, and natural language processing, as has been advocated for previously (McClelland et al., 2019; Lake and Murphy, 2020).”
Understanding Natural Language Understanding Systems. A Critical Analysis (2023, background): “A similar view is expressed by Lake and Murphy (2021), who regard even the latest and most sophisticated DSMs as quite far from being psychologically plausible models of meaning, because they are not connected with perception, action, and reasoning.”
The debate over understanding in AI’s large language models (2022, background): “It has been argued that understanding of this kind may enable abilities not possible for purely statistical models [19, 27, 44, 66, 76].”
Talking about Large Language Models (2022, background): “BOT: This yields the full prompt to be submitted to the LLM, which will hopefully predict a con-4”
One-Shot Learning from a Demonstration with Hierarchical Latent Language (2022, unknown): “We frame the contribution of our new demonstration following environment and our proposed HLLP agent in terms of Lake and Murphy (2021)’s ﬁve desiderata for a computational theory of semantics characteristic of human language use: 1.”
Improving Coherence and Consistency in Neural Sequence Models with Dual-System, Neuro-Symbolic Reasoning (2021, background): “Lake & Murphy (2020) illustrated several of these issues with GPT-2 (Radford et al., 2019).”