Investigating Different Syntactic Context Types and Context Representations for Learning Word Embeddings

@inproceedings{Li2017InvestigatingDS,
  title={Investigating Different Syntactic Context Types and Context Representations for Learning Word Embeddings},
  author={Bofang Li and T. Liu and Zhe Zhao and Buzhou Tang and Aleksandr Drozd and Anna Rogers and X. Du},
  booktitle={EMNLP},
  year={2017}
}
The number of word embedding models is growing every year. Most of them are based on the co-occurrence information of words and their contexts. However, it is still an open question what is the best definition of context. We provide a systematical investigation of 4 different syntactic context types and context representations for learning word embeddings. Comprehensive experiments are conducted to evaluate their effectiveness on 6 extrinsic and intrinsic tasks. We hope that this paper, along… Expand
28 Citations
A Deeper Look into Dependency-Based Word Embeddings
  • 9
  • PDF
Revisiting the Context Window for Cross-lingual Word Embeddings
  • Highly Influenced
  • PDF
Towards Qualitative Word Embeddings Evaluation: Measuring Neighbors Variation
  • 17
  • Highly Influenced
  • PDF
Predicting Word Embeddings Variability
  • 15
  • PDF
PBoS: Probabilistic Bag-of-Subwords for Generalizing Word Embedding
  • PDF
What's in Your Embedding, And How It Predicts Task Performance
  • 21
  • PDF
Word Embedding Algorithms as Generalized Low Rank Models and their Canonical Form
  • 2
  • PDF
Scaling Word2Vec on Big Corpus
  • 11
  • PDF
Subword-level Composition Functions for Learning Word Embeddings
  • 15
  • PDF
...
1
2
3
...

References

SHOWING 1-10 OF 53 REFERENCES
The Role of Context Types and Dimensionality in Learning Word Embeddings
  • 95
  • Highly Influential
  • PDF
Learning Word Meta-Embeddings
  • 62
  • PDF
How to Generate a Good Word Embedding
  • 229
  • PDF
Tailoring Continuous Word Representations for Dependency Parsing
  • 280
  • PDF
Intrinsic Evaluations of Word Embeddings: What Can We Do Better?
  • 68
  • PDF
Learning Syntactic Categories Using Paradigmatic Representations of Word Context
  • 42
  • PDF
Intrinsic Evaluation of Word Vectors Fails to Predict Extrinsic Performance
  • 81
  • PDF
...
1
2
3
4
5
...