Transformer_Temporal_Tagger
Transformer_Temporal_Tagger copied to clipboard
satya77
Code and data form the paper BERT Got a Date: Introducing Transformers to Temporal Tagging
I am using this code to load the model and the tokenizer: ``` tokenizer = AutoTokenizer.from_pretrained("satyaalmasian/temporal_tagger_DATEBERT_tokenclassifier", use_fast=False) model = tr.BertForTokenClassification.from_pretrained("satyaalmasian/temporal_tagger_DATEBERT_tokenclassifier") ``` I have a list of text: `examples=['Texas DRIVER LICENSE...
Hello, I have been unable to unzip this data.zip file. Is it possibly broken? Additionally, is there pre-processed Seq2Seq available for download? (uploading as a Huggingface dataset would be awesome)...
Hi, I am trying to use this model for inference but the plain text tagging comes out to be very weird. Input: "Hello, today is Monday but not Tuesday, maybe...
First, thank you for the great work! Just want to bring to your attention that the [latest arXiv version (v3)](https://arxiv.org/abs/2109.14927) is not available. Any possibility of seeing the v3 published...
Hey there, I'm getting the following error and I'm not sure what is causing it. /opt/conda/lib/python3.9/site-packages/temporal_taggers/evaluation/tagger_evaluation.py(152)place_timex_tag() 150 import pdb 151 pdb.set_trace() --> 152 print(f"Remaining raw text: {raw_text}") 153 raise ValueError(f"Could...
For samples that exceed the 512 subword token limit, we currently do not have a strategy in place to deal with this. This is both unwanted and relatively easy to...
This might in fact be a problem with the wider functionality of the seq2seq examples, I'll take a look next week.
The link to the fine-tuning guide on the Hugging Face model card for "temporal_tagger_BERT_tokenclassifier" appears to be unavailable: https://huggingface.co/satyaalmasian/temporal_tagger_BERT_tokenclassifier
