Sub-Word Similarity based Search for Embeddings: Inducing Rare-Word Embeddings for Word Similarity Tasks and Language Modelling

Mittul Singh, Clayton Greenberg, Youssef Oualil, Dietrich Klakow


Abstract
Training good word embeddings requires large amounts of data. Out-of-vocabulary words will still be encountered at test-time, leaving these words without embeddings. To overcome this lack of embeddings for rare words, existing methods leverage morphological features to generate embeddings. While the existing methods use computationally-intensive rule-based (Soricut and Och, 2015) or tool-based (Botha and Blunsom, 2014) morphological analysis to generate embeddings, our system applies a computationally-simpler sub-word search on words that have existing embeddings. Embeddings of the sub-word search results are then combined using string similarity functions to generate rare word embeddings. We augmented pre-trained word embeddings with these novel embeddings and evaluated on a rare word similarity task, obtaining up to 3 times improvement in correlation over the original set of embeddings. Applying our technique to embeddings trained on larger datasets led to on-par performance with the existing state-of-the-art for this task. Additionally, while analysing augmented embeddings in a log-bilinear language model, we observed up to 50% reduction in rare word perplexity in comparison to other more complex language models.
Anthology ID:
C16-1194
Volume:
Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers
Month:
December
Year:
2016
Address:
Osaka, Japan
Venue:
COLING
SIG:
Publisher:
The COLING 2016 Organizing Committee
Note:
Pages:
2061–2070
Language:
URL:
https://aclanthology.org/C16-1194
DOI:
Bibkey:
Cite (ACL):
Mittul Singh, Clayton Greenberg, Youssef Oualil, and Dietrich Klakow. 2016. Sub-Word Similarity based Search for Embeddings: Inducing Rare-Word Embeddings for Word Similarity Tasks and Language Modelling. In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pages 2061–2070, Osaka, Japan. The COLING 2016 Organizing Committee.
Cite (Informal):
Sub-Word Similarity based Search for Embeddings: Inducing Rare-Word Embeddings for Word Similarity Tasks and Language Modelling (Singh et al., COLING 2016)
Copy Citation:
PDF:
https://preview.aclanthology.org/starsem-semeval-split/C16-1194.pdf