On the Information Content of Predictions in Word Analogy Tests
Not on the map. Why?
Abstract (arXiv)
An approach is proposed to quantify, in bits of information, the actual relevance of analogies in analogy tests. The main component of this approach is a softaccuracy estimator that also yields entropy estimates with compensated biases. Experimental results obtained with pre-trained GloVe 300-D vectors and two public analogy test sets show that proximity hints are much more relevant than analogies in analogy tests, from an information content perspective. Accordingly, a simple word embedding model is used to predict that analogies carry about one bit of information, which is experimentally corroborated.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 7 of its 27 references that are in the map. First posted on arXiv 18 Oct 2022.
Builds on
7 of 27 references.
References · 7
- 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,346
- 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,462
- 2014word2vec Explained: deriving Mikolov et al.'s negative-sampling word-embedding methodcited by 109
- 2016Issues in evaluating semantic spaces using word analogiescited by 26
- 2016Problems With Evaluation of Word Embeddings Using Word Similarity Taskscited by 25
- 2020Analogies minus analogy test: measuring regularities in word embeddingscited by 17
- 2018An Analysis of Hierarchical Text Classification Using Word Embeddingscited by 16
Built on by
Not cited yet.