2014 CompositionalMorphologyforWordR

• (Botha & Blunsom, 2014) ⇒ Jan A. Botha, and Phil Blunsom. (2014). “Compositional Morphology for Word Representations and Language Modelling.” In: Proceedings of the 31th International Conference on Machine Learning, (ICML 2014).

Subject Headings: Word Embedding System; SumEmbed System, Compositional Morphological Representation System.

Cited By

• Google Scholar: ~ 257 Citations.

Quotes

Abstract

This paper presents a scalable method for integrating compositional morphological representations into a vector-based probabilistic language model. Our approach is evaluated in the context of log-bilinear language models, rendered suitably efficient for implementation inside a machine translation decoder by factoring the vocabulary. We perform both intrinsic and extrinsic evaluations, presenting results on a range of languages which demonstrate that our model learns morphological representations that both perform well on word similarity tasks and lead to substantial reductions in perplexity. When used for translation into morphologically rich languages with large vocabularies, our models obtain improvements of up to 1.2 BLEU points relative to a baseline system using back-off n-gram models.

BibTeX

@inproceedings{2014_CompositionalMorphologyforWordR,
  author    = {Jan A. Botha and
               Phil Blunsom},
  title     = {Compositional Morphology for Word Representations and Language Modelling},
  booktitle = {Proceedings of the 31th International Conference on Machine Learning,
               (ICML 2014)},
  series    = {JMLR Workshop and Conference Proceedings},
  volume    = {32},
  pages     = {1899--1907},
  publisher = {JMLR.org},
  year      = {2014},
  url       = {http://proceedings.mlr.press/v32/botha14.html},
}

---

	Author	volume	Date Value	title	type	journal	titleUrl	doi	note	year
2014 CompositionalMorphologyforWordR	Phil Blunsom Jan A. Botha			Compositional Morphology for Word Representations and Language Modelling						2014