Xiulin Yang comments

Results 11 comments of


                                            Xiulin Yang

Is there a way to convert the generated AMRs to the original format?

I have one more question: How do you deal with ill-formed AMRs? I find that sometimes the number connects with the relations like :mod1234.

does this model runs silently ? After giving the command "python train.py best" it is at one state for 2hr

Hey did you figure it out? I'm having the same problem too.

how to understand the head_word_emb in the initial file ,glove_50_300_2.txt,how to get the file?

> is this file pretrained by using Glove word embeddings with a window size 2? Hey, did you figure it out? I'm curious about it too. :)

REMATCH: Robust and Efficient Matching of Local Knowledge Graphs to Improve Structural and Semantic Similarity

Thanks!

[Question]: I got different results when I loaded a trained model to do the inference task on the same test data

Hi @alanakbik, thanks a lot for your prompt reply! :) I tried to use ColumnCorpus in Flair (as seen below) but the issue remains. Is it possible for me to...

[Question]: I got different results when I loaded a trained model to do the inference task on the same test data

Hi, just a quick update. I tried the other task (upos tagging) but the result is still weird. I created a [Google Colab script](https://colab.research.google.com/drive/1UFPKgH1r1RXPDy8si5Ev0-T1Xdk5ia_d?usp=sharing) to replicate the experiment. It will...