Distributed Representations of Words and Phrases and Their Compositionality¶
Mikolov, T., Sutskever, I., Chen, K., Corrado, G. S., & Dean, J. (2013). Distributed Representations of Words and Phrases and Their Compositionality. Advances in Neural Information Processing Systems 26.
Cited by¶
4 citations across 4 artifacts.
Each citation links to the sentence it supports in the citing article.
Primes¶
- Embedding
- The guest is a discrete vocabulary of several hundred thousand tokens, whose native structure is semantic relatedness — "king" is to "queen" as "man" is to "woman," "Paris" sits near "France."
This sourceWord2vec: discrete tokens placed in a real vector space so semantic relatedness becomes geometric proximity, supporting analogy and nearest-neighbor operations.
- The guest is a discrete vocabulary of several hundred thousand tokens, whose native structure is semantic relatedness — "king" is to "queen" as "man" is to "woman," "Paris" sits near "France."
- Paradigmatic vs. Syntagmatic Relations
- Modern word-embeddings (Mikolov 2013,
This sourceMikolov word2vec word-embeddings distributional semantics paradigmatic proximity.
- Modern word-embeddings (Mikolov 2013,
- Signifier–Signified Duality
- Artificial Intelligence and Natural Language Processing (Mikolov 2013, Pennington et al. 2014): Modern word-embeddings (word2vec, GloVe) operationalize Saussure's insight about systemic-differential meaning: word meaning is captured as a vector in high-dimensional space, where meaning is relational position, not absolute property.
This sourceMikolov word2vec distributional semantics word-embeddings vector space.
- Artificial Intelligence and Natural Language Processing (Mikolov 2013, Pennington et al. 2014): Modern word-embeddings (word2vec, GloVe) operationalize Saussure's insight about systemic-differential meaning: word meaning is captured as a vector in high-dimensional space, where meaning is relational position, not absolute property.
- Vector Space
- Vector embeddings turned discrete objects — words, users, products — into vectors so that geometry encodes similarity, enabling clustering, recommendation, and analogy reasoning, with the classic king − man + woman ≈ queen exploiting vector-space structure directly.
This sourceWord embeddings where analogy is a displacement vector — king - man + woman ~ queen, and cosine similarity measures relatedness as an angle.
- Vector embeddings turned discrete objects — words, users, products — into vectors so that geometry encodes similarity, enabling clustering, recommendation, and analogy reasoning, with the classic king − man + woman ≈ queen exploiting vector-space structure directly.
Verification¶
This reference passed the adversarial substantiation pipeline: it was checked to exist and to support the claim it is attached to. See how references were verified.
Links previously used in the corpus¶
Before the registry existed this work was also linked 1 other way.
Registry ID ref:bf8026d0d6cf · see in the full table