-
Your study is an interesting contribution.
I have a shallow question: Do you have used BERT only as a tokenizer in a subword level?
Anyway, as the source code will give more details about, i'll appr…
-
It seems like it use ntee model for pre-rank without training it. It is wield. Can you provide the trained weights of ntee model?
-
Based on my understanding, ELMo first init an word embedding matrix `A` for all the word and then add LSTM `B`, at end use the LSTM `B`'s outputs to predict each word's next word.
I am wondering wh…
-
Hi, how can I use this huggingface pretrained model to produce chengyu embeddings? https://huggingface.co/visualjoyce/chengyubert_2stage_stage1_wwm_ext ,
since chinese-BERT-wwm only produces token ba…
-
Hi,
Thanks for the great work. The LSTM tutorial looks very nice.
Are any suggestions on how to use Captum for Transformer-based / BERT-like pre-trained contextualized word embeddings? If I want to …
-
Hey, I saw this issue and I wanted to get the P(word|topic)
https://github.com/MaartenGr/BERTopic/issues/144
You suggested accessing it using `model.c_tf_idf`, but I still need the words that were…
-
Hi,
great work!
I saw your autoregression branch and wanted to ask if it worked out?
I always wondered how much the effect of the autoregression (apart from the formal aspect that it then is a au…
-
I have trained declutur on legal dataset and I am trying to use it to extract topics using CTM.Currently process runs for infinite time without showing any output. Any idea why CTM does not work here.…
-
**Describe the bug**
open_base.py训练有bug
mat1 and mat2 shapes cannot be multiplied (800x256 and 768x1536)
**Code to reproduce the issue**
```
# -*- coding:utf-8 -*-
# Author: hankcs
# Dat…
-
In the[ presented example](https://colab.research.google.com/github/agemagician/ProtTrans/blob/master/Embedding/TensorFlow/Advanced/ProtBert-BFD.ipynb#scrollTo=X67IzakrwZfS), for using ProtBert-BFD-TF…