BilBOWA: Fast Bilingual Distributed Representations without Word Alignments

author: Stephan Gouws, MIH Media Lab, Stellenbosch University
published: Dec. 5, 2015,   recorded: October 2015,   views: 20
Categories

See Also:

Download slides icon Download slides: icml2015_gouws_word_alignments_01.pdf (3.3┬áMB)


Help icon Streaming Video Help

Related content

Report a problem or upload files

If you have found a problem with this lecture or would like to send us extra material, articles, exercises, etc., please use our ticket system to describe your request and upload the data.
Enter your e-mail into the 'Cc' field, and we will keep you updated with your request's status.
Lecture popularity: You need to login to cast your vote.
  Bibliography

Description

We introduce BilBOWA (Bilingual Bag-of-Words without Alignments), a simple and computationally-efficient model for learning bilingual distributed representations of words which can scale to large monolingual datasets and does not require word-aligned parallel training data. Instead it trains directly on monolingual data and extracts a bilingual signal from a smaller set of raw-text sentence-aligned data. This is achieved using a novel sampled bag-of-words cross-lingual objective, which is used to regularize two noise-contrastive language models for efficient cross-lingual feature learning. We show that bilingual embeddings learned using the proposed model outperforms state-of-the-art methods on a cross-lingual document classification task as well as a lexical translation task on the WMT11 data.

Link this page

Would you like to put a link to this lecture on your homepage?
Go ahead! Copy the HTML snippet !

Write your own review or comment:

make sure you have javascript enabled or clear this field: