search

kevinscaria / InstructABSA

Instructional learning for Aspect Based Sentiment Analysis [NAACL-2024]
https://aclanthology.org/2024.naacl-short.63/
MIT License
147 stars 24 forks source link

Aspect Sentiment Triplet Extraction #15

Closed xiaokening closed 1 year ago

xiaokening commented 1 year ago

Have you tried to use the instruction learning paradigm for Aspect Sentiment Triplet Extraction?

kevinscaria commented 1 year ago

Yes, we are working on it. Will update it soon.

Keep-lucky commented 1 year ago

Yes, we are working on it. Will update it soon.

Hello, I would like to make modifications to your code for the Aspect Sentiment Triplet Extraction task. Could you please provide me with some guidance and ideas?

kevinscaria commented 1 year ago

hey Sure, what ideas/guidance do you need?

Keep-lucky commented 1 year ago

hey Sure, what ideas/guidance do you need?

Could you provide me with some guidance on which specific parts of the code to modify for the Aspect Sentiment Triplet Extraction task, in order to avoid unnecessary changes? Additionally, when can we expect your ASTE work to be published? I would like to use it as a reference for comparison. Thank you！

kevinscaria commented 1 year ago

The ASTE work will be updated in the paper only in October unfortunately. But I will share results in the github readme within a week or two. The only changes you will need to make would in the utils.py and data_prep.py. If you use scripts for running, you will have to change run_model.py.

I recently pushed the codes for aoste task too. The code currently will work for AOSTE task. If you want a running script, I will share it with you shortly. It is barebones script that I currently used for running my experiments.

kevinscaria commented 1 year ago

Oh wait the data_prep is incorrect. It is just a placeholder right now. I will update it sorry.

Keep-lucky commented 1 year ago

Oh wait the data_prep is incorrect. It is just a placeholder right now. I will update it sorry.

Thank you very much for your response. I will patiently await the release of your work. If I have any further questions, I will continue to consult with you. Please kindly offer me your guidance. Wishing you a successful work!