GithubHelp home page GithubHelp logo

damo-nlp-sg / bgca Goto Github PK

View Code? Open in Web Editor NEW
29.0 29.0 4.0 1.96 MB

[ACL 2023] Code and Data for "Bidirectional Generative Framework for Cross-domain Aspect-based Sentiment Analysis"

License: MIT License

Python 95.81% Shell 4.19%
aspect-based-sentiment-analysis natural-language-processing nlp

bgca's People

Contributors

ntudy avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar

bgca's Issues

NotImplementedError

Traceback (most recent call last):
File "C:\Users\孤星\Desktop\BGCA-master\code\main.py", line 328, in
runed_dirs = run_multiple_seeds(args, seed_list)
File "C:\Users\孤星\Desktop\BGCA-master\code\main.py", line 320, in run_multiple_seeds
raise NotImplementedError
NotImplementedError

AOPE task TypeError

When I try to run the AOPE task, I get the following error:
File "C:\Users\LXL\Desktop\experiment\BGCA-master\code\data_utils.py", line 258, in prepare_uabsa_universal
tag_token = TAG_TO_SPECIAL[tag][0]
TypeError: unhashable type: 'list'
1
I found that other tasks pass in ["pos"], but this task passes in a list of numbers. How can I modify it?

Question about the formulas

Thank you for the knowledge in your research article. I have read and understood the ideas of the methods.
However, I encountered some ambiguities in some of the formulas. For example, formula 2, what is (l) (sequence of ...), why does (i) start from -1.
It would be valuable if I received a detailed explanation for this formula, and if possible, for each of formulas 2, 3, 5, 6.
Thank you very much!

Questions about the quantity of generating data

Thanks for your outstanding Contribution ❤️, your data augmentation method is very novel! After carefully reading your papaer, there's one quesiton that would like to consult:

Is the quantity of unlabeled dats used for generation pseudo label always one-to-one ? Is it feasible that generating multiple pseudo data given one sample?

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.