Analogy-based detection of morphological and semantic relations with word embeddings: what works and what doesn't

@inproceedings{Rogers2016AnalogybasedDO,
  title={Analogy-based detection of morphological and semantic relations with word embeddings: what works and what doesn't},
  author={Anna Rogers and Aleksandr Drozd and S. Matsuoka},
  booktitle={SRW@HLT-NAACL},
  year={2016}
}
Following up on numerous reports of analogybased identification of “linguistic regularities” in word embeddings, this study applies the widely used vector offset method to 4 types of linguistic relations: inflectional and derivational morphology, and lexicographic and encyclopedic semantics. We present a balanced test set with 99,200 questions in 40 categories, and we systematically examine how accuracy for different categories is affected by window size and dimensionality of the SVD-based word… Expand
118 Citations
What's in Your Embedding, And How It Predicts Task Performance
  • 21
  • PDF
Understanding the Source of Semantic Regularities in Word Embeddings
  • 2
  • Highly Influenced
  • PDF
Fitting Semantic Relations to Word Embeddings
  • Highly Influenced
  • PDF
Analogy-based Assessment of Domain-specific Word Embeddings
  • Highly Influenced
Analogies minus analogy test: measuring regularities in word embeddings
  • 2
  • Highly Influenced
  • PDF
Assessing Lexical-Semantic Regularities in Portuguese Word Embeddings
  • PDF
Production of Large Analogical Clusters from Smaller Example Seed Clusters Using Word Embeddings
  • 1
  • PDF
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 36 REFERENCES
Multilingual Reliability and "Semantic" Structure of Continuous Word Spaces
  • 38
  • PDF
Extracting semantic representations from word co-occurrence statistics: stop-lists, stemming, and SVD
  • 253
  • PDF
Linguistic Regularities in Continuous Space Word Representations
  • 2,723
  • Highly Influential
  • PDF
Linguistic Regularities in Sparse and Explicit Word Representations
  • 572
  • PDF
Glove: Global Vectors for Word Representation
  • 17,629
  • Highly Influential
  • PDF
Learning Effective Word Embedding using Morphological Word Similarity
  • 6
  • PDF
...
1
2
3
4
...