Content 此篇論文主要完成了:1.通過數(shù)學(xué)推導(dǎo)汰蓉，找到并證明了限制RNN-based LMs的性能瓶頸之一——Softmax Bottleneck問題2.針對(duì)這個(gè)瓶頸，提...
發(fā)簡(jiǎn)信
IP屬地：浙江
-
Breaking the Softmax Bottleneck:A High-rank RNN Language Model -
讀萬卷書饲帅，行萬里路矛绘。<br><br>記錄那些讀過的書籍。
-
深度學(xué)習(xí)的Nan問題
相信很多人都遇到過訓(xùn)練一個(gè)deep model的過程中辱匿，loss突然變成了NaN键痛。在這里對(duì)這個(gè)問題做一個(gè)總結(jié)。 一般來說匾七，出現(xiàn)NaN有以下幾種情況： 如果在迭代的100輪以內(nèi)...
-
2018 · NAACL · BP · Deep Contextualized Word Representations
2018 · NAACL · BP · Deep Contextualized Word Representations 問題：以往的詞向量表示的語義信息并不豐富絮短，沒有挖掘到...
-
2018 · NIPS · Learned in Translation: Contextualized Word Vectors
2018 · NIPS · Learned in Translation: Contextualized Word Vectors 想法來源：從CV中借鑒的想法，深層的神經(jīng)網(wǎng)...
-
2018 · ICLR · A NEW METHOD OF REGION EMBEDDING FOR TEXT CLASSIFICATION
2018 · ICLR · A NEW METHOD OF REGION EMBEDDING FOR TEXT CLASSIFICATION 想法來源：為了挖掘深層的語法信息...
-
2018 · ICLR · SKIP RNN: LEARNING TO SKIP STATE UPDATES IN RECURRENT NEURAL NETWORKS
2018 · ICLR · SKIP RNN: LEARNING TO SKIP STATE UPDATES IN RECURRENT NEURAL NETWORKS 想法來...
-
2018· ACL · Unsupervised Learning of Sentence Embeddings using Compositional n-Gram Features
2018· ACL · Unsupervised Learning of Sentence Embeddings using Compositional n-Gram Fea...
-
2018 · ACL · Some of Them Can be Guessed! Exploring the Effect of Linguistic Context in Predictin...
2018 · ACL · Some of Them Can be Guessed! Exploring the Effect of Linguistic Context in...
-
2018 · ACL · LSTMs Exploit Linguistic Attributes of Data
2018 · ACL · LSTMs Exploit Linguistic Attributes of Data 想法來源：實(shí)驗(yàn)性質(zhì)文章昨忆。主要是測(cè)試LSTM的記憶能力丁频。 價(jià)值...
-
2018 · ACL · Exploring Semantic Properties of Sentence Embeddings
2018 · ACL · Exploring Semantic Properties of Sentence Embeddings 想法來源：探索性實(shí)驗(yàn)性質(zhì)文章。 價(jià)值：可以...
-
2017 · ICLR · EFFICIENT VECTOR REPRESENTATION FOR DOCUMENTS THROUGH CORRUPTION
2017 · ICLR · EFFICIENT VECTOR REPRESENTATION FOR DOCUMENTS THROUGH CORRUPTION 想法來源：文檔表...
-
2018 · ACL · What you can cram into a single $&!#* vector-Probing sentence embeddings for linguis...
2018 · ACL · What you can cram into a single $&!#* vector-Probing sentence embeddings f...
-
2017 · EMNLP · Supervised Learning of Universal Sentence Representations from Natural Language In...
2017 · EMNLP · Supervised Learning of Universal Sentence Representations from Natural L...
-
2017 · ICLR · A STRUCTURED SELF-ATTENTIVE SENTENCE EMBEDDING
2017 · ICLR · A STRUCTURED SELF-ATTENTIVE SENTENCE EMBEDDING · 想法來源：監(jiān)督任務(wù)+self-attention...
-
2016 · ICLR · IMPROVING PERFORMANCE OF RECURRENT NEURAL NETWORK WITH RELU NONLINEARITY
2016 · ICLR · IMPROVING PERFORMANCE OF RECURRENT NEURAL NETWORK WITH RELU NONLINEARITY ...
-
2018 · ICLR · AN EFFICIENT FRAMEWORK FOR LEARNING SENTENCE REPRESENTATIONS
2018 · ICLR · AN EFFICIENT FRAMEWORK FOR LEARNING SENTENCE REPRESENTATIONS · 想法來源：文章從分布...
-
2017 · Arxiv · Discourse-Based Objectives for Fast Unsupervised Sentence Representation Learning ·
2017 · Arxiv · Discourse-Based Objectives for Fast Unsupervised Sentence Representation...
-
2017 · TACL · Enriching Word Vectors with Subword Information
想法來源：很多的詞向量表達(dá)都是將詞作為單一體來看待的邑贴，沒有考慮參數(shù)的共享席里。從感知角度來說，就是失去了原有的內(nèi)部結(jié)構(gòu)拢驾。 價(jià)值：a. 學(xué)習(xí)到詞與詞形態(tài)學(xué)方面的信息奖磁，詞與詞交集越多...
-
EMNLP · 2017 · Mimicking Word Embeddings using Subword RNNs
EMNLP · 2017 · Mimicking Word Embeddings using Subword RNNs · 想法來源：subword 價(jià)值：利用了subwor...
個(gè)人介紹