arXiv Open Access 2017

Reconstruction of Word Embeddings from Sub-Word Parameters

Karl Stratos

Lihat Sumber

Abstrak

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.

Topik & Kata Kunci

cs.CL

Penulis (1)

Karl Stratos

Format Sitasi

APA MLA BibTeX

Stratos, K. (2017). Reconstruction of Word Embeddings from Sub-Word Parameters. https://arxiv.org/abs/1707.06957

Akses Cepat

Lihat di Sumber

Informasi Jurnal

Tahun Terbit: 2017
Bahasa: en
Sumber Database: arXiv
Akses: Open Access ✓