發(fā)簡信
IP屬地：重慶
相信很多人都遇到過訓(xùn)練一個deep model的過程中，loss突然變成了NaN。在這里對這個問題做一個總結(jié)。 一般來說，出現(xiàn)NaN有以下幾種情...
2018 · NAACL · BP · Deep Contextualized Word Representations 問題：以往的詞向量表示...
2018 · NIPS · Learned in Translation: Contextualized Word Vectors 想法來源：從...
2018 · ICLR · A NEW METHOD OF REGION EMBEDDING FOR TEXT CLASSIFICATION 想...
2018 · ICLR · SKIP RNN: LEARNING TO SKIP STATE UPDATES IN RECURRENT NEUR...
2018· ACL · Unsupervised Learning of Sentence Embeddings using Compositi...
2018 · ACL · Some of Them Can be Guessed! Exploring the Effect of Lingui...
2018 · ACL · LSTMs Exploit Linguistic Attributes of Data 想法來源：實驗性質(zhì)文章。主要是...
2018 · ACL · Exploring Semantic Properties of Sentence Embeddings 想法來源：探...