Git Product home page Git Product logo

Comments (7)

vzhong avatar vzhong commented on July 21, 2024

Yes I think there is a bug here - the matching is supposed to be done as follows:

-    indices = [i for i, c in enumerate(context) if c == '*']
+    indices = [i for i, c in enumerate(context) if c['sub'] == '*']
     pairs = list(zip(indices, indices[1:] + [len(context)]))
     cleaned = []
     for s, e in pairs:
-        while not context[e-1].strip():
+        while not context[e-1]['sub'].strip():
             e -= 1
-        while not context[s].strip() or context[s] == '*':
+        while not context[s]['sub'].strip() or context[s]['sub'] == '*':
             s += 1
         if e - s > 2 and e - 2 < 45:
             cleaned.append((s, e-1))

from e3.

vzhong avatar vzhong commented on July 21, 2024

I'm rerunning the training scripts to see if this changes results

from e3.

Yifan-Gao avatar Yifan-Gao commented on July 21, 2024

Can you add your preprocessed files into docker environment? I will see if I can replicate your results with your processed files.

from e3.

vzhong avatar vzhong commented on July 21, 2024

OK, after I retrained the model for the retrieval:

Best dev
{'dev_bleu_1': 0.5175,
 'dev_bleu_2': 0.4804,
 'dev_bleu_3': 0.4532,
 'dev_bleu_4': 0.4288,
 'dev_combined': 0.31851264,
 'dev_macro_accuracy': 0.7428,
 'dev_micro_accuracy': 0.6881,
 'dev_span_f1': 0.7758598345984843,
 'epoch': 3,
 'train_bleu_1': 0.5795,
 'train_bleu_2': 0.548,
 'train_bleu_3': 0.5282,
 'train_bleu_4': 0.5141,
 'train_combined': 0.44541623999999996,
 'train_loss_clf': 0.40613971317808967,
 'train_loss_retrieve': 0.2112928715934799,
 'train_loss_span_end': 0.011150807250163897,
 'train_loss_span_start': 0.017885973322182485,
 'train_macro_accuracy': 0.8664,
 'train_micro_accuracy': 0.834,
 'train_span_f1': 1.0}

For the editor

Best dev
{'dev_f1': 0.7611304248405354,
 'epoch': 11,
 'train_f1': 0.8762811226505095,
 'train_loss_after': 0.4524998854104321,
 'train_loss_before': 0.640820378238715}

And for the joint inference

{'bleu_1': 0.6645,
 'bleu_2': 0.6045,
 'bleu_3': 0.566,
 'bleu_4': 0.5395,
 'combined': 0.3957772,
 'macro_accuracy': 0.7336,
 'micro_accuracy': 0.6802}

from e3.

vzhong avatar vzhong commented on July 21, 2024

fixed in 0c6b771

from e3.

vzhong avatar vzhong commented on July 21, 2024

Can you add your preprocessed files into docker environment? I will see if I can replicate your results with your processed files.

Not sure if this helps but here's the content of my preprocessed sharc folder: https://drive.google.com/file/d/1hdmcEE5JRRvzB2qjFF1iEqL536XSowPt/view?usp=sharing

from e3.

Yifan-Gao avatar Yifan-Gao commented on July 21, 2024

Thanks, now I can replicate your results with your trained model and processed files on a cuda8 environment.

{'bleu_1': 0.667,
 'bleu_2': 0.6041,
 'bleu_3': 0.5635,
 'bleu_4': 0.5362,
 'combined': 0.39335632000000004,
 'macro_accuracy': 0.7336,
 'micro_accuracy': 0.6802}

I am going to figure out where the problem is.

from e3.

Related Issues (5)

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.