embeddings   331

« earlier    

[1805.01070] What you can cram into a single vector: Probing sentence embeddings for linguistic properties
Although much effort has recently been devoted to training high-quality sentence embeddings, we still have a poor understanding of what they are capturing. "Downstream" tasks, often based on sentence classification, are commonly used to evaluate the quality of sentence representations. The complexity of the tasks makes it however difficult to infer what kind of information is present in the representations. We introduce here 10 probing tasks designed to capture simple linguistic features of sentences, and we use them to study embeddings generated by three different encoders trained in eight distinct ways, uncovering intriguing properties of both encoders and training methods.
embeddings  evaluation 
27 days ago by foodbaby
bheinzerling/bpemb: Pre-trained subword embeddings in 275 languages, based on Byte-Pair Encoding (BPE)
Pre-trained subword embeddings in 275 languages, based on Byte-Pair Encoding (BPE) - bheinzerling/bpemb
embedding  embeddings  bpe  deep-learning  nlp  oov 
28 days ago by nharbour

« earlier    

related tags

acl-2018  ai  airbnb  articles_to_read  bert  bias  bilm  bioinformatics  books  bpe  cardinality  categorical  classification  cnn  code  code2vec  compression  cooking  cosine-distance  course  data  data_science  datasets  deep-learning  deep_learning  deeplearning  demo  development  dl  ebooks  elmo  embedding  evaluation  everything  facebook  fasttext  fine-tuning  food  generative  glove  google  health  hierarchicalembeddings  howto  image  imagerecognition  images  index  ip-address  ir  keras  language-models  language  lda2vec  learning  lib  library  lm  lstm  machine-learning  machine_learning  machinelearning  mapping  maps  medicine  medium  mikolov  ml-interpretability  ml  model  models  moz  multilingual  music  natural-language  network  neural-networks  ngram  ngrams  nlp  nlproc  nlu  oov  opensource  paper  papers  poincarreembeddings  python  qa  quantization  questionanswersystems  recipes  recommendations  reference  research  resources  rnn  rudder  ruder  search  sentence  senteval  sentiment_analysis  similarity  skip-gram  spacy  sparse  squad  starspace  t-sne  teaching  tensorflow  text_analysis  textanalysis  todo  tools  topic-modeling  topic  torch  transfer-learning  transferlearning  translation  tutorial  tweetit  unsupervised_learning  visualization  webtools  wikipedia  wikipedia2vec  word-embeddings  word-vector  word  word2vec  wordembedding  workshop  workshopper 

Copy this bookmark: