Finding Function in Form: Compositional Character Models for Open Vocabulary Word Representation

@inproceedings{Ling2015FindingFI,
  title={Finding Function in Form: Compositional Character Models for Open Vocabulary Word Representation},
  author={Wang Ling and Chris Dyer and A. Black and I. Trancoso and Ram{\'o}n Fern{\'a}ndez Astudillo and Silvio Amir and Lu{\'i}s Marujo and T. Lu{\'i}s},
  booktitle={EMNLP},
  year={2015}
}
We introduce a model for constructing vector representations of words by composing characters using bidirectional LSTMs. Relative to traditional word representation models that have independent vectors for each word type, our model requires only a single vector per character type and a fixed set of parameters for the compositional model. Despite the compactness of this model and, more importantly, the arbitrary nature of the form‐function relationship in language, our “composed” word… Expand
530 Citations
Character and Subword-Based Word Representation for Neural Language Modeling Prediction
  • 11
  • PDF
A Character-Word Compositional Neural Language Model for Finnish
  • 6
  • Highly Influenced
  • PDF
Learning to Create and Reuse Words in Open-Vocabulary Neural Language Modeling
  • 30
  • PDF
Generalizing Word Embeddings using Bag of Subwords
  • 25
  • Highly Influenced
  • PDF
Language Modeling for Morphologically Rich Languages: Character-Aware Modeling for Word-Level Prediction
  • 28
  • PDF
A Joint Model for Word Embedding and Word Morphology
  • 59
  • Highly Influenced
  • PDF
Character-based Neural Machine Translation
  • 109
  • PDF
Enriching Word Vectors with Subword Information
  • 4,738
  • PDF
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 49 REFERENCES
Compositional Morphology for Word Representations and Language Modelling
  • 208
  • PDF
Better Word Representations with Recursive Neural Networks for Morphology
  • 725
  • PDF
Joint Learning of Character and Word Embeddings
  • 206
  • PDF
Improved Transition-based Parsing by Modeling Characters instead of Words with LSTMs
  • 273
  • PDF
Learning Character-level Representations for Part-of-Speech Tagging
  • 475
  • Highly Influential
  • PDF
Two/Too Simple Adaptations of Word2Vec for Syntax Problems
  • 306
  • PDF
Recurrent Continuous Translation Models
  • 1,079
  • PDF
When Are Tree Structures Necessary for Deep Learning of Representations?
  • 192
  • PDF
Paraphrasing 4 Microblog Normalization
  • 49
  • PDF
...
1
2
3
4
5
...