@article{hashimoto-etal-2016-word,
    title = "Word Embeddings as Metric Recovery in Semantic Spaces",
    author = "Hashimoto, Tatsunori B.  and
      Alvarez-Melis, David  and
      Jaakkola, Tommi S.",
    journal = "Transactions of the Association for Computational Linguistics",
    volume = "4",
    year = "2016",
    address = "Cambridge, MA",
    publisher = "MIT Press",
    url = "https://aclanthology.org/Q16-1020",
    doi = "10.1162/tacl_a_00098",
    pages = "273--286",
    abstract = "Continuous word representations have been remarkably useful across NLP tasks but remain poorly understood. We ground word embeddings in semantic spaces studied in the cognitive-psychometric literature, taking these spaces as the primary objects to recover. To this end, we relate log co-occurrences of words in large corpora to semantic similarity assessments and show that co-occurrences are indeed consistent with an Euclidean semantic space hypothesis. Framing word embedding as metric recovery of a semantic space unifies existing word embedding algorithms, ties them to manifold learning, and demonstrates that existing algorithms are consistent metric recovery methods given co-occurrence counts from random walks. Furthermore, we propose a simple, principled, direct metric recovery algorithm that performs on par with the state-of-the-art word embedding and manifold learning methods. Finally, we complement recent focus on analogies by constructing two new inductive reasoning datasets{---}series completion and classification{---}and demonstrate that word embeddings can be used to solve them as well.",
}