allenai/specter

Issues

• Training data and code to reproduce model training

  #2 opened 4 years ago by urmeya
  3

• Format specified for json file containing title and abstract is wrong.

  #50 opened 2 years ago by coolshr
  0

• Fine-tuning SPECTER?

  #20 opened 4 years ago by jacklxc
  3

• json.decoder.JSONDecodeError: Expecting property name enclosed in double quotes: line 1 column 2 (char 1)

  #28 opened 3 years ago by rrsun
  1

• concat_title_abstract must be True in scripts/pytorch_lightning_training_script/train.py#L73

  #49 opened 2 years ago by piegu
  1

• RoBERTa instead of BERT: what changes in SPECTER scripts?

  #48 opened 2 years ago by piegu
  0

• How to create the vocab files? (tokens.txt, non_padded_namespaces.txt, venue.txt)

  #45 opened 2 years ago by piegu
  5

• Does the model use Bert's vocabulary or scibert's vocabulary, or do they all use it? Where is it used

  #43 opened 2 years ago by humdingers
  1

• How to set num_train_instances when using your pickled training data

  #14 opened 4 years ago by lulujianjie
  4

• ERROR: Allennlp params.py ValueError: Cannot convert variable to bool: all

  #42 opened 2 years ago by humdingers
  0

• where can I get the dataset used in the paper?

  #41 opened 2 years ago by BinbinJin
  1

• Using trained model: which tokenizer?

  #38 opened 3 years ago by mle-els
  0

• Matching articles from SPECTER's dataset with S2ORC IDs

  #37 opened 3 years ago by zoranmedic
  1

• Positive paper sampling

  #36 opened 3 years ago by malteos
  2

• ArrayField.empty_field problem with DatasetReader

  #27 opened 3 years ago by pjuangph
  6

• Code does not go to completion when `njobs` is greater than 1

  #35 opened 3 years ago by abhi1nandy2
  1

• Use custom dataset without hard negatives

  #34 opened 3 years ago by ryangawei
  0

• Create preprocessed training files: metadata.json is missing ids in the train.txt, test.txt and val.txt

  #13 opened 4 years ago by shauryr
  6

• How to train my own model with other checkpoints?

  #33 opened 3 years ago by ryangawei
  0

• How to change the sequence length?

  #31 opened 3 years ago by nshinton
  1

• How to deal with this bug?

  #32 opened 3 years ago by dandandandan77
  0

• Training Data Set for Spectre

  #29 opened 3 years ago by ringkasannet
  5

• Can we get calculated embeddings directly into variable?

  #10 opened 4 years ago by kieron15
  12

• Error when training: "None" is not a <Class 'allennlp.data.fields.field.Field'>

  #30 opened 3 years ago by ringkasannet
  1

• Model name 'data/scibert_scivocab_uncased/vocab.txt' was not found in model name list

  #25 opened 3 years ago by nshinton
  2

• cannot import name 'import_submodules' from 'allennlp.common.util'

  #16 opened 4 years ago by Horsmann
  2

• Nan loss in training specter with specter/scripts/pytorch_lightning_training_script/train.py

  #26 opened 3 years ago by AlexRossi6
  0

• Huggingface model produces different embeddings

  #24 opened 4 years ago by malteos
  3

• Confused about the Huggingface Usage (using ' ' instead of '[SEP]' for concatenating)

  #22 opened 4 years ago by Punchwes
  2

• Any plans to make the model available on the Transformers library?

  #17 opened 4 years ago by rodrigonogueira4
  4

• query regarding information retrieval using text query

  #18 opened 4 years ago by MukundVarmaT
  1

• Streaming data for inferrence

  #11 opened 4 years ago by ckald
  2

• How to correctly define "--included-text-fields" when embedding data

  #15 opened 4 years ago by cl600class
  3

• Label namespace warning

  #12 opened 4 years ago by DWFlanagan
  2

• Help required for training data preparation

  #3 opened 4 years ago by victor714
  4

• Question regarding train / val / test split

  #9 opened 4 years ago by victor714
  3

• KeyError: 'authors' while trying to get article embeddings

  #6 opened 4 years ago by urmeya
  1

• How to install this model in the docker

  #5 opened 4 years ago by freshnemo
  1

• I am wondering when exactly will the model and data be released?

  #1 opened 4 years ago by Penny1012
  4

• To get Embeddings for research papers and reviews

  #4 opened 4 years ago by rajevv
  2