2016 MorphologicalPriorsforProbabili

• (Bhatia et al., 2016) ⇒ Parminder Bhatia, Robert Guthrie, and Jacob Eisenstein. (2016). “Morphological Priors for Probabilistic Neural Word Embeddings.” In: Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing (EMNLP 2016).

Subject Headings: Word Embedding System; VarEmbed System; SumEmbed System; Probabilistic Neural Word Embedding System.

Cited By

• Google Scholar: ~ 37 Citations.

Quotes

Abstract

Word embeddings allow natural language processing systems to share statistical information across related words. These embeddings are typically based on distributional statistics, making it difficult for them to generalize to rare or unseen words. We propose to improve word embeddings by incorporating morphological information, capturing shared sub-word features. Unlike previous work that constructs word embeddings directly from morphemes, we combine morphological and distributional information in a unified probabilistic framework, in which the word embedding is a latent variable. The morphological information provides a prior distribution on the latent word embeddings, which in turn condition a likelihood function over an observed corpus. This approach yields improvements on intrinsic word similarity evaluations, and also in the downstream task of part-of-speech tagging.

BibTeX

@inproceedings{2016_MorphologicalPriorsforProbabili,
  author    = {Parminder Bhatia and
               Robert Guthrie and
               Jacob Eisenstein},
  editor    = {Jian Su and
               Xavier Carreras and
               Kevin Duh},
  title     = {Morphological Priors for Probabilistic Neural Word Embeddings},
  booktitle = {Proceedings of the 2016 Conference on Empirical Methods in Natural
               Language Processing (EMNLP 2016)},
  pages     = {490--500},
  publisher = {The Association for Computational Linguistics},
  year      = {2016},
  url       = {https://doi.org/10.18653/v1/d16-1047},
  doi       = {10.18653/v1/d16-1047},
}

---

	Author	volume	Date Value	title	type	journal	titleUrl	doi	note	year
2016 MorphologicalPriorsforProbabili	Jacob Eisenstein Robert Guthrie Parminder Bhatia			Morphological Priors for Probabilistic Neural Word Embeddings						2016