arXiv:1707.06957
Reconstruction of Word Embeddings from Sub-Word Parameters
원문 초록
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.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
A Comparative Analysis of Static Word Embeddings for Hungarian
Analyzing Continuous Semantic Shifts with Diachronic Word Similarity Matrices
LGDE: Local Graph-based Dictionary Expansion
VNLP: Turkish NLP Package
myNER: Contextualized Burmese Named Entity Recognition with Bidirectional LSTM and fastText Embeddings via Joint Training with POS Tagging
Exploring transfer learning for Deep NLP systems on rarely annotated languages
토론
이 논문과 연결된 포럼 글이 아직 없습니다.