QMSum

QMSum copied to clipboard

Hi, what means relevant_text_span, can you exlpain it in details? Is it the start and end indexes of user speeches? Shouldn't it be a index of sentences?

BMukhtar

target for Locator?

2

Hi， I'm very interested in your Locator and trying to reproduce the model. However, there are still some questions that confused me. As the paper says, the Locator is trained...

pangsg

Hi, in your QMSum paper, the 5.1 Implementation Details section mentioned that you used fairseq library to implement BART model and you truncate the input text to 2048 tokens. Did...

zhangyao1994

The number of Test.

1

Why did I processed 281 test sets and 279 in this paper? Is there something wrong ?

RoyZhanyi

Hello, this is great work! It seems like you have done some tentatives on the HMNet. Could you please provide the method for how to define the role vector for...

YebowenHu

pretrained locator

1

Hi, Could you provide the model and code of the locator?

ethanhe42

potential incorrect annotation

7

Hi, I am manually checking the data annotation. I randomly pick one file in the test set, which is Bed008.json. In my opinion, the annotations are a bit problematic. See...

chijames