search

fani-lab / LADy

LADy 💃: A Benchmark Toolkit for Latent Aspect Detection Enriched with Backtranslation Augmentation
Other
5 stars 6 forks source link

Loader for XML-based Semeval Datasets #7

Closed hosseinfani closed 1 year ago

hosseinfani commented 2 years ago

Currently, the code has a loader for a csv file (not sure if it's from semeval). We need to add a loader for the official semeval datasets

hosseinfani commented 1 year ago

@DeepKaran1 Congrats! You got your first real task. Can you give me an estimate of when you will finish this task?

DeepKaran1 commented 1 year ago

@hosseinfani Previously I was busy with my exams and just started working on it today. I am unsure about how much time it requires in total from me, instead you can give me a deadline for this, and I will try to finish it before that.

hosseinfani commented 1 year ago

@DeepKaran1 how about a week from now?

DeepKaran1 commented 1 year ago

Dr. Fani I am afraid, as I am in Toronto spending some quality time with my family it will be quite challenging for me, but I will try my best to complete it.

farinamhz commented 1 year ago

I need to change the preprocessing on the XML dataset and change the way of tokenizing the sentences to get the index of aspect words.

hosseinfani commented 1 year ago

@farinamhz also, one remaining task was make the vicabularly the same for all methods.

farinamhz commented 1 year ago

Hi @hosseinfani, I have updated the XML loader based on what we talked about for tokenizing method. The vocabulary updates for what you said will be done under issue ( #12 ). Thanks for reminding this task.