%0 Conference Proceedings %T Reconstruction of Word Embeddings from Sub-Word Parameters %A Stratos, Karl %Y Faruqui, Manaal %Y Schuetze, Hinrich %Y Trancoso, Isabel %Y Yaghoobzadeh, Yadollah %S Proceedings of the First Workshop on Subword and Character Level Models in NLP %D 2017 %8 September %I Association for Computational Linguistics %C Copenhagen, Denmark %F stratos-2017-reconstruction %X Pre-trained word embeddings improve the performance of a neural model at the cost of increasing the model size. We propose to benefit from this resource without paying the cost by operating strictly at the sub-lexical level. Our approach is quite simple: before task-specific training, we first optimize sub-word parameters to reconstruct pre-trained word embeddings using various distance measures. We report interesting results on a variety of tasks: word similarity, word analogy, and part-of-speech tagging. %R 10.18653/v1/W17-4119 %U https://aclanthology.org/W17-4119 %U https://doi.org/10.18653/v1/W17-4119 %P 130-135