Just Keep Happy
Convs2s-MT Convs2s-MT
Title《Convolutional Sequence to Sequence Learning》 Abstract We introduce an architecture based entirely on convolutional
2020-10-09 PaperLookThrough
MT CNN NLP
dynamaticonv dynamaticonv
Title《Pay Less Attention With Lightweight and Dynamic Convolutions](https://arxiv.org/abs/1901.10430)》 Abstract self-att
2020-10-07 PaperLookThrough
MT CNN NLP
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
MT book MT book
统计机器翻译3.基于词的机器翻译模型3.1 词在翻译中的作用先把句子中的每个词对应翻译后重新排序。包括三个步骤：分析、转换、生成。 3.2构建简单的机器翻译系统 人为翻译：翻译知识的学习（翻译候选），运用知识生成译文（处理常见的单词搭配、主
2020-09-20 BookLook
MT NLP
code structure code structure
nlp经典论文集 http://www.marekrei.com/blog/74-summaries-of-machine-learning-and-nlp-research/ prerequisite MLemail bert相比于Tr
2020-08-29 Code
code structure
neo4j neo4j
一、Basic conceptsExample graph： 1.Nodes：represent entities2.Labels：group nodes into sets by a certain label[^one node can
2020-08-29 Commontools
database neo4j
juice recipe juice recipe
一、果昔[^Tips:if you want to make juice stickier,you can add some avocado(牛油果)]: 1.avocado+apple+mint(薄荷) taste: 2.mango+p
2020-08-28 food
juice
Wuenda's class(2) Wuenda's class(2)
p1.Train/dev/test sets Train：训练集，用来训练各种模型 dev：验证集(development set)/Hold-out cross validation set，评估这些模型，通过迭代选出最优模型 test：
2020-08-20 VideoClass
deep-learning
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
4 / 5