Skip to content

Latest commit

 

History

History
21 lines (21 loc) · 677 Bytes

README.md

File metadata and controls

21 lines (21 loc) · 677 Bytes
Raw

word embedding

.
├── BiCCA	 		# BiCCA model
├── eval			# evaluation method
├── README.md
└── utiutility

Bilingual Word Embedding

BiCCA model

Faruqui M, Dyer C. Improving vector space word representations using multilingual correlation[C]. Association for Computational Linguistics, 2014. open source: https://github.com/mfaruqui/eacl14-cca

file
  • cal_word_pair.py: computing the bilingual vocabulary.
  • BiCCA.py: BiCCA model

translation evaluation

  • eval/words_sim.py: script
  • eval/bldict: blingual dictionary evaluating the cross-lingual model

utility

  • VecConvert.py: convert BiCVM output to Word2Vec output