Word meaning in minds and machines

• URL: http://arxiv.org/abs/2008.01766v3
• Date: Sat, 17 Apr 2021 21:05:02 GMT
• Title: Word meaning in minds and machines
• Authors: Brenden M. Lake and Gregory L. Murphy
• Abstract summary: 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. We discuss more promising approaches to grounding NLP systems and argue that they will be more successful with a more human-like, conceptual basis for word meaning.
• Score: 18.528929583956725
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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 more promising approaches to grounding NLP systems and argue that they will be more successful with a more human-like, conceptual basis for word meaning.

Related papers

• A Philosophical Introduction to Language Models -- Part I: Continuity With Classic Debates [0.05657375260432172]
  This article serves both as a primer on language models for philosophers, and as an opinionated survey of their significance. We argue that the success of language models challenges several long-held assumptions about artificial neural networks. This sets the stage for the companion paper (Part II), which turns to novel empirical methods for probing the inner workings of language models.
  arXiv  Detail & Related papers  (2024-01-08T14:12:31Z)
• Visual cognition in multimodal large language models [12.603212933816206]
  Recent advancements have rekindled interest in the potential to emulate human-like cognitive abilities. This paper evaluates the current state of vision-based large language models in the domains of intuitive physics, causal reasoning, and intuitive psychology.
  arXiv  Detail & Related papers  (2023-11-27T18:58:34Z)
• A Sentence is Worth a Thousand Pictures: Can Large Language Models Understand Hum4n L4ngu4ge and the W0rld behind W0rds? [2.7342737448775534]
  Large Language Models (LLMs) have been linked to claims about human-like linguistic performance. We analyze the contribution of LLMs as theoretically informative representations of a target cognitive system. We evaluate the models' ability to see the bigger picture, through top-down feedback from higher levels of processing.
  arXiv  Detail & Related papers  (2023-07-26T18:58:53Z)
• From Word Models to World Models: Translating from Natural Language to the Probabilistic Language of Thought [124.40905824051079]
  We propose rational meaning construction, a computational framework for language-informed thinking. We frame linguistic meaning as a context-sensitive mapping from natural language into a probabilistic language of thought. We show that LLMs can generate context-sensitive translations that capture pragmatically-appropriate linguistic meanings. We extend our framework to integrate cognitively-motivated symbolic modules.
  arXiv  Detail & Related papers  (2023-06-22T05:14:00Z)
• MEWL: Few-shot multimodal word learning with referential uncertainty [24.94171567232573]
  We introduce the MachinE Word Learning benchmark to assess how machines learn word meaning in grounded visual scenes. MEWL covers human's core cognitive toolkits in word learning: cross-situational reasoning, bootstrapping, and pragmatic learning. By evaluating multimodal and unimodal agents' performance with a comparative analysis of human performance, we notice a sharp divergence in human and machine word learning.
  arXiv  Detail & Related papers  (2023-06-01T09:54:31Z)
• Machine Psychology [54.287802134327485]
  We argue that a fruitful direction for research is engaging large language models in behavioral experiments inspired by psychology. We highlight theoretical perspectives, experimental paradigms, and computational analysis techniques that this approach brings to the table. It paves the way for a "machine psychology" for generative artificial intelligence (AI) that goes beyond performance benchmarks.
  arXiv  Detail & Related papers  (2023-03-24T13:24:41Z)
• Talking About Large Language Models [7.005266019853958]
  The more adept large language models become, the more vulnerable we become to anthropomorphism. This paper advocates the practice of repeatedly stepping back to remind ourselves of how LLMs, and the systems of which they form a part, actually work. The hope is that increased scientific precision will encourage more philosophical nuance in the discourse around artificial intelligence.
  arXiv  Detail & Related papers  (2022-12-07T10:01:44Z)
• Emergence of Machine Language: Towards Symbolic Intelligence with Neural Networks [73.94290462239061]
  We propose to combine symbolism and connectionism principles by using neural networks to derive a discrete representation. By designing an interactive environment and task, we demonstrated that machines could generate a spontaneous, flexible, and semantic language.
  arXiv  Detail & Related papers  (2022-01-14T14:54:58Z)
• Perspective-taking and Pragmatics for Generating Empathetic Responses Focused on Emotion Causes [50.569762345799354]
  We argue that two issues must be tackled at the same time: (i) identifying which word is the cause for the other's emotion from his or her utterance and (ii) reflecting those specific words in the response generation. Taking inspiration from social cognition, we leverage a generative estimator to infer emotion cause words from utterances with no word-level label.
  arXiv  Detail & Related papers  (2021-09-18T04:22:49Z)
• My Teacher Thinks The World Is Flat! Interpreting Automatic Essay Scoring Mechanism [71.34160809068996]
  Recent work shows that automated scoring systems are prone to even common-sense adversarial samples. We utilize recent advances in interpretability to find the extent to which features such as coherence, content and relevance are important for automated scoring mechanisms. We also find that since the models are not semantically grounded with world-knowledge and common sense, adding false facts such as the world is flat'' actually increases the score instead of decreasing it.
  arXiv  Detail & Related papers  (2020-12-27T06:19:20Z)
• Bongard-LOGO: A New Benchmark for Human-Level Concept Learning and Reasoning [78.13740873213223]
  Bongard problems (BPs) were introduced as an inspirational challenge for visual cognition in intelligent systems. We propose a new benchmark Bongard-LOGO for human-level concept learning and reasoning.
  arXiv  Detail & Related papers  (2020-10-02T03:19:46Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.