Adaptive Input Representations
2000년 도입 · 논문 66편에서 사용
Adaptive Input Embeddings extend the adaptive softmax to input word representations. The factorization assigns more capacity to frequent words and reduces the capacity for less frequent words with the benefit of reducing overfitting to rare words.
출처: Adaptive Input Representations for Neural Language Modeling
소개 논문: Adaptive Input Representations for Neural Language Modeling
Input Embedding Factorization · Natural Language Processing