A new way of finding analogues as an opportunity to study language, thinking and build artificial intelligence systems

The article presents a new method for obtaining analogues of words, characterized by simplicity and the absence of the need for preliminary training on large data as in existing methods. In the method under study, analogues are determined by their syntactic predicates using methods of distributive semantics. In the study, analogues of adjectives, nouns and verbs were obtained and analyzed. This made it possible to obtain a result that is not inferior to the results obtained using the most popular neural network approach as word2vec when qualitatively comparing analogues. The demonstrated method shows that obtaining analogues is possible using methods of distributive semantics using a more interpretable method, which opens up the possibility of studying semantic analogy. This method also allows you to identify analogues on a specific topic. Based on the experimental results obtained, an original definition of analogues and cognitive schemes is formulated. The article also analyzes and substantiates the possibility of a new approach for creating artificial intelligence systems based on the researched method. According to the authors, this provides significant advantages for the creation of such systems. In particular, the proposed method allows for broader generalizations over orders of magnitude smaller data, as well as learning during use, which is not possible for neural networks.

1. Mikolov Т., Chen К., Corrado G., Dean J. Efficient Estimation of Word Representations in Vector Space. https://arxiv.org/abs/1301.3781.

2. Mitchell M. Idiot or genius? How does artificial intelligence work and what is it capable of. Publishing: Corpus House, 2022. P. 120‑145.

3. Anna Rogers, Aleksandr Drozd, Bofang Li. The (too Many) Problems of Analogical Reasoning with Word Vectors. Available. January 2017. https://www.researchgate.net/publication/318741605.

4. Aleksandr Drozd, Anna Rogers, Satoshi Matsuoka. Word Embeddings, Analogies, and Machine Learning. December 2016. https://www.researchgate.net/publication/311843169.

5. Carl Allen, Timothy Hospedales. Analogies Explained: Towards Understanding Word Embeddings. https://arxiv.org/abs/1901.09813.

6. Falcon Z. Dai, Word2vec Conjecture and ALimitative Result. https://arxiv.org/abs/2010.12719.

7. Michael SC Thomas and Denis Mareschal. 1997. Connectionism and psychological notions of similarity. In The Proceedings of the 19th Annual Conference of the Cognitive Science Society. Mahwah, NJ: Erlbaum, Stanford, USA. P. 757‑762. http://eprints.bbk.ac.uk/4611.

8. Louis Fournier, Ewan Dunbar, Paraphrases do not explain word analogies. https://arxiv.org/abs/2102.11749.

9. Tomáš Musil. Semantic Holism and Word Representations in Artificial Neural Networks. https://arxiv.org/abs/2003.05522.

10. Tal Linzen. Issues in evaluating semantic spaces using word analogies. https://arxiv.org/abs/1606.07736.

11. Paul Bartha. 2016. Analogy and analogical reason‑ing. In Edward N. Zalta, editor, The StanfordEncyclopedia of Philosophy, Metaphysics ResearchLab, Stanford University. Winter 2016 edition. https://plato.stanford.edu/archives/win2016/entries/reasoning-analogy.

12. Katrin Erk. What do you know aboutan alligator when you know the company itkeeps. Semantics and Pragmatics 9(17):1‑63. 2016. https://semprag.org/index.php/sp/article/view/sp.9.17.