hiersumm

hiersumm copied to clipboard

Hi Thanks for sharing the code. After implementing Hierarchical Transformers, I found there is a difference in the residual connection between figure 2 and the code. In [here](https://github.com/nlpyang/hiersumm/blob/476e6bf9c716326d6e4c27d5b6878d0816893659/src/abstractive/transformer_encoder.py#L178), the input...

zhiqihuang

.pt files generation of own dataset

8

Hi! Thank you for the code. I successfully evaluated your model. Now i am interested in extracting summaries for my own dataset. Can you please guide me how to extract...

Zirsha

data change?

2

Hi,nlpyang!Thank you very much for your open source @nlpyang I have a question to ask you : if your model are trained in other languages , such as Chinese. How...

bultiful

Custom dataset

1

Is there a simple way to train and evaluate the model on a custom dataset?

darsh10

Please if anyone has this code worked with custom data, I need a help: - how to create the .pt files? - how to create the vocab file? and does...

Tinarights

Hi, I got an error when reading the vocab file: spm9998_3.model RuntimeError: Internal: /sentencepiece/python/bundled/sentencepiece/src/sentencepiece_processor.cc(823) [model_proto->ParseFromArray(serialized.data(), serialized.size())] When I google it, they said the file is not in the correct format....

Tinarights

Hi Yang, Thank you for sharing the code. In file 'train_abstractive.py', I would like to know what's the meaning of 'EOT', 'EOP' and 'EOQ' in line 244.

Alvacc

how to load spm9998_3.model file?

1

Dear Mr. Liu, I'm studying your paper “Hierarchical Transformers for Multi-Document Summarization” and code, and I'm a new learner in this task. Recently, I wanna use your code to run...

LGDEMO

Encoder dropout default value error

1

When trying to evaluate the trained model by using the specified arguments in the README, I get "**ValueError: dropout probability has to be between 0 and 1, but got 6**"....

martin-kirilov

How to generate summary after loading the model ?

4

I am new to this, can you please guide me how to generate summary after successfully loading the pretrained model. I have used this command to load the pretrained model...

vishaljoshi-066