Corpus ID: 7202537

Word Embeddings, Analogies, and Machine Learning: Beyond king - man + woman = queen

@inproceedings{Drozd2016WordEA,
  title={Word Embeddings, Analogies, and Machine Learning: Beyond king - man + woman = queen},
  author={Aleksandr Drozd and Anna Rogers and S. Matsuoka},
  booktitle={COLING},
  year={2016}
}
Solving word analogies became one of the most popular benchmarks for word embeddings on the assumption that linear relations between word pairs (such as king:man :: woman:queen) are indicative of the quality of the embedding. We question this assumption by showing that the information not detected by linear offset may still be recoverable by a more sophisticated search method, and thus is actually encoded in the embedding. The general problem with linear offset is its sensitivity to the… Expand
77 Citations
Rotate King to get Queen: Word Relationships as Orthogonal Transformations in Embedding Space
  • 5
  • PDF
Analogies minus analogy test: measuring regularities in word embeddings
  • 2
  • PDF
An Optimality Proof for the PairDiff operator for Representing Relations between Words
  • 1
  • PDF
Understanding the Source of Semantic Regularities in Word Embeddings
  • 2
  • Highly Influenced
  • PDF
Assessing Lexical-Semantic Regularities in Portuguese Word Embeddings
  • Highly Influenced
  • PDF
Discovering linguistic (ir)regularities in word embeddings through max-margin separating hyperplanes
  • 1
  • Highly Influenced
  • PDF
Inducing Relational Knowledge from BERT
  • 38
  • PDF
Relation Induction in Word Embeddings Revisited
  • 16
  • Highly Influenced
  • PDF
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 33 REFERENCES
Rehabilitation of Count-Based Models for Word Vector Representations
  • 44
  • PDF
Linguistic Regularities in Sparse and Explicit Word Representations
  • 572
  • PDF
Linguistic Regularities in Continuous Space Word Representations
  • 2,723
  • Highly Influential
  • PDF
Glove: Global Vectors for Word Representation
  • 17,629
  • Highly Influential
  • PDF
Learning Effective Word Embedding using Morphological Word Similarity
  • 6
  • PDF
Improving Distributional Similarity with Lessons Learned from Word Embeddings
  • 1,029
  • Highly Influential
  • PDF
Analogy-based detection of morphological and semantic relations with word embeddings: what works and what doesn't
  • 118
  • PDF
A Uniform Approach to Analogies, Synonyms, Antonyms, and Associations
  • 203
  • PDF
Category Enhanced Word Embedding
  • 4
  • Highly Influential
  • PDF
...
1
2
3
4
...