Combining Distributed Vector Representations for Words

@inproceedings{Garten2015CombiningDV,
  title={Combining Distributed Vector Representations for Words},
  author={Justin Garten and Kenji Sagae and Volkan Ustun and Morteza Dehghani},
  booktitle={VS@HLT-NAACL},
  year={2015}
}
Recent interest in distributed vector representations for words has resulted in an increased diversity of approaches, each with strengths and weaknesses. We demonstrate how diverse vector representations may be inexpensively composed into hybrid representations, effectively leveraging strengths of individual components, as evidenced by substantial improvements on a standard word analogy task. We further compare these results over different sizes of training sets and find these advantages are… Expand
24 Citations

Tables from this paper

Asynchronous Training of Word Embeddings for Large Text Corpora
  • 2
  • PDF
Meta-Embedding Sentence Representation for Textual Similarity
  • PDF
dish2vec: A Comparison of Word Embedding Methods in an Unsupervised Setting
  • Highly Influenced
  • PDF
Bayesian Neural Word Embedding
  • 61
  • PDF
Leveraging Meta-Embeddings for Bilingual Lexicon Extraction from Specialized Comparable Corpora
  • 6
  • PDF
Word Embeddings, Analogies, and Machine Learning: Beyond king - man + woman = queen
  • 77
  • Highly Influenced
  • PDF
Bilingual Word Embeddings for Bilingual Terminology Extraction from Specialized Comparable Corpora
  • 8
  • Highly Influenced
  • PDF
What Analogies Reveal about Word Vectors and their Compositionality
  • 16
  • PDF
Reusing Weights in Subword-aware Neural Language Models
  • 2
  • PDF
...
1
2
3
...

References

SHOWING 1-10 OF 17 REFERENCES
Efficient Estimation of Word Representations in Vector Space
  • 17,528
  • Highly Influential
  • PDF
Distributed Vector Representations of Words in the Sigma Cognitive Architecture
  • 15
  • PDF
Linguistic Regularities in Sparse and Explicit Word Representations
  • 572
  • PDF
Dependency-Based Word Embeddings
  • 756
  • PDF
Linguistic Regularities in Continuous Space Word Representations
  • 2,723
  • PDF
Representation Learning: A Review and New Perspectives
  • 7,182
  • PDF
Low-Rank Tensors for Scoring Dependency Structures
  • 111
  • PDF
Indexing by Latent Semantic Analysis
  • 8,018
  • PDF
Ensemble Methods in Machine Learning
  • 5,390
  • PDF
...
1
2
...