Just Keep Happy
  Post Categories
软件工具 6 PaperLookThrough 19 BookLook 2 food 1 VideoClass 2 Code 3 Commontools 2 VedioLearning 1 PaperLookThroughy 3 Origin PaperLookThrough 4 Model summary 1 conceptual record 1 NN 1
Multi-Scale attention-seq Multi-Scale attention-seq
Title《MUSE: PARALLEL MULTI-SCALE ATTENTION FOR SEQUENCE TO SEQUENCE LEARNING》 AbstractQ:attention mechanism alone suffer
2020-10-06 PaperLookThrough
MT NLP attention
deep transformer-NMT deep transformer-NMT
Title:《Very Deep Transformers for Neural Machine Translation》 Q：how to decrease the variance of the output layer in orde
2020-10-06 PaperLookThrough
MT Admin NLP
Back-Translation Back-Translation
title:《Understanding Back-Translation at Scale》Q:how to improve neural machine translation with monolingual data? S:augm
2020-10-06 PaperLookThrough
MT Transformer NLP
Task-Oriented Dialogue as Dataflow Synthesis Task-Oriented Dialogue as Dataflow Synthesis
《Task-Oriented Dialogue as Dataflow Synthesis》一、对话系统的问题和挑战 短句包括多个指示。 人类语言具有长尾性，无法使用高频意图覆盖 [^长尾性：系统中的个体相差悬殊，缺乏优选]: 多轮对
2020-09-28 PaperLookThrough
MT NLP
Word Representation-Sememes Word Representation-Sememes
Abstract Sememes are minimum semantic units of word meanings, and the meaning of each word sense is typically composed b
2020-08-12 PaperLookThrough
NLP WRL - WSD
MRC for NER MRC for NER
titleA Unified MRC Framework for Named Entity Recognition Abstract:The task of named entity recognition (NER) is normal
2020-07-10 PaperLookThrough
-NER -实体重叠
3 / 4