Giter Club home page Giter Club logo

Comments (5)

Coopercoppers avatar Coopercoppers commented on July 29, 2024

您好,我来回答一下您的问题

  1. 是单轮的训练结果。全部实验都是random seed = 0,因为encoding scheme比较重要,所以我在webnlg上也是做过测试的,sequential和parallel大概比joint低个0.5-1.5点左右。SciERC结果不稳定,想能问下浮动能大到多少呢?浮动大的原因可能是超参没有怎么调,可以试试一些稳定训练的trick,比如说warmup等。
  2. entity extraction确实会出现您说的这种情况,这部分可能是RE部分没有cover实体尾部的结果,可以试试PFN-nested。
  3. 这个没有做过。因为没有partition,也就得不到三个分区了,这样的话也就不知道是对哪个部分进行filter了。

from pfn.

wcwowwwww avatar wcwowwwww commented on July 29, 2024
  1. 我使用了您的代码,重新运行了在seed = [0,1,2,3,4]的情况。NER的结果在65.67-68.59,RE的结果在36.23到37.86。方差还是比较大的。
  2. 如果方便的话,请问您是否可以在ablation study添加上entity extraction的结果呢?看到您的代码是同时输出NER和RE两个结果的。

非常感谢您的回答。希望您科研顺利。

from pfn.

Coopercoppers avatar Coopercoppers commented on July 29, 2024

RE结果和我这差的有点多。我跑了下1,2,3,4的seed,NER的结果是66.9, 66.4, 68.0, 67.7, RE的结果是36.9, 36.3, 38.9, 37.7。我在readme上更新了cuda版本要求,貌似这个也是会有影响的。

ablation我这里只存了sequential和parallel,sequential是68.7, parallel是67.0,scierc上确实波动很大,这部分我觉得可能是因为训练数据集本身的原因导致的。webnlg上NER sequential和parallel比joint差个0.3-0.5左右。

由于论文是最终稿,emnlp不让改了,所以可能没法添加结果。希望上边几个数值对您有用。

from pfn.

wcwowwwww avatar wcwowwwww commented on July 29, 2024

好的,谢谢您的回复。论文中的内容虽然无法额外变动,但是希望能够在github项目的readme上更新实验结果。同时建议您的ablation study能够在5-10个random seed上取NER和RE的平均结果和方差。单次的RE结果恐怕不能够使得您论文中ablation study的结论令人信服。

from pfn.

Coopercoppers avatar Coopercoppers commented on July 29, 2024

嗯,谢谢您的建议,ablation的多次结果之后会考虑加上的。

from pfn.

Related Issues (20)

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.