Grounding the Vector Space of an Octopus: Word Meaning from Raw Text
Open accessThe DOI matches its Crossref record; 18 of the 18 references it cites were found in a registry or an index.
Abstract
Most, if not all, philosophers agree that computers cannot learn what words refers to from raw text alone. While many attacked Searle’s Chinese Room thought experiment, no one seemed to question this most basic assumption. For how can computers learn something that is not in the data? Emily Bender and Alexander Koller (2020) recently presented a related thought experiment—the so-called Octopus thought experiment, which replaces the rule-based interlocutor of Searle’s thought experiment with a neural language model. The Octopus thought experiment was awarded a best paper prize and was widely debated in the AI community. Again, however, even its fiercest opponents accepted the premise that what a word refers to cannot be induced in the absence of direct supervision. I will argue that what a word refers to is probably learnable from raw text alone. Here’s why: higher-order concept co-occurrence statistics are stable across languages and across modalities, because language use (universally) reflects the world we live in (which is relatively stable). Such statistics are sufficient to establish what words refer to. My conjecture is supported by a literature survey, a thought experiment, and an actual experiment.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173
Searle, J. R. (1980) · Behavioral and Brain Sciences · doi:10.1017/s0140525x00005756 · Cited by 6,954
Searle, J. R. (1992) · doi:10.7551/mitpress/5834.001.0001 · Cited by 3,595
Language identification in the limit
Gold, E. M. (1967) · Information and Control · doi:10.1016/s0019-9958(67)91165-5 · Cited by 3,572 · cited 1×
“3 Note how this is orthogonal to Gold (1967), arguing that grammar cannot be acquired from raw text: Even if language was subregular and learnable in the limit, meaning would not necessarily be learnable.”
BackgroundGeneralized procrustes analysis
Gower, J. C. (1975) · Psychometrika · doi:10.1007/bf02291478 · Cited by 3,267 · cited 2×
“If weak super-vision is available, we can use techniques such as Procrustes Analysis (Gower, 1975) or Iterative Closest Point (Besl & McKay, 1992), but aligments can be obtained in the absence of any supervision using adversarial learning (Li et al., 2019; Søgaard et al., 2019) or distributional evidence alone.”
MethodKuhl, P. K., Tsao, F.-M., & Liu, H.-M. (2003) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1532872100 · Cited by 1,237 · cited 1×
“Kuhl (Kuhl et al., 2003) herself found that infants’ attention to people is much stronger than attention to inanimate objects.”
BackgroundPredicting Human Brain Activity Associated with the Meanings of Nouns
Mitchell, T. M., Shinkareva, S. V., Carlson, A., Chang, K.-M., Malave, V. L., Mason, R. A., & Just, M. A. (2008) · Science · doi:10.1126/science.1152876 · Cited by 1,180 · cited 1×
“Other research articles that seem to suggest that language model representations are generally isomorphic to brain activity patterns include (Mitchell et al., 2008; Søgaard, 2016; Wehbe et al., 2014; Pereira et al., 2018; Gauthier & Levy, 2019; Caucheteux & King, 2022).”
BackgroundClimbing towards NLU: On Meaning, Form, and Understanding in the Age of Data
Bender, E. M., & Koller, A. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.463 · Cited by 1,082 · cited 12×
“(Bender & Koller 2020, p. 5191) I will distinguish between three questions: 1.”
BackgroundMethodInfluentialUnsupervised Machine Translation Using Monolingual Corpora Only
Lample, G., Conneau, A., Denoyer, L., & Ranzato, M. (2017) · arXiv · doi:10.48550/arxiv.1711.00043 · Cited by 584 · cited 1×
“Consider, for example, the fact that unsupervised machine translation is possible (Lample et al., 2018a, b; Park et al., 2021).”
Background
Cited by
Eight Things to Know about Large Language Models
Bowman, S. R. (2023) · arXiv · doi:10.48550/arxiv.2304.00612 · Cited by 137
Mathew, R., & Stefaniak, J. E. (2024) · TechTrends · doi:10.1007/s11528-024-00964-z · Cited by 15
The bewitching AI: The Illusion of Communication with Large Language Models
Bottazzi Grifoni, E., & Ferrario, R. (2025) · Philosophy & Technology · doi:10.1007/s13347-025-00893-6 · Cited by 15
Are Large Language Models Intentional? The Limits of Referential Grounding
García-Valdecasas, M. (2026) · Philosophy & Technology · doi:10.1007/s13347-026-01079-4 · Cited by 6
“In a similar vein, Søgaard (2023) argues that LLMs can be grounded in text alone because language universally reflects world structure.”
Metadata
- Authors
- Søgaard, A.
- Venue
- Minds and Machines
- Published
- 2023-01-23
- Volume
- 33
- Issue
- 1
- Pages
- 33-54
- ISSN
- 0924-6495 (ISSN-L)
- 1572-8641
- OpenAlex
- W4317797582
- Cited by
- 46
- References
- 18
- FWCI
- 4.04
- Type
- journal article
- Language
- en
- Open access
- hybrid
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Grounding the Vector Space of an Octopus: Word Meaning from Raw Text. https://app.cochat.ai/papers/10.1007/s11023-023-09622-4
- The paper
- Søgaard, A. (2023). Grounding the Vector Space of an Octopus: Word Meaning from Raw Text. Minds and Machines. https://doi.org/10.1007/s11023-023-09622-4
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.