lx865712528 / acl2019-odee Goto Github PK
View Code? Open in Web Editor NEWThis is the code for our ACL 2019 paper "Open Domain Event Extraction Using Neural Latent Variable Models"
This is the code for our ACL 2019 paper "Open Domain Event Extraction Using Neural Latent Variable Models"
看了你的论文和代码,发现你并没有使用到论文中提及的8个slot固定槽而是通过corenlp**指的类型规定slot的,关于评估标准P、R和F的代码都有缺失,还有就是代码中无论训练测试都是整个数据集在做这是不是存在问题呢?希望能够得到解答
Hello, I read the paper you published at the ACL 2019 conference, I am very interested, and found your implementation code through github. When I reproduce your experiment, I found that t-SNE visualization is missing from your code. Because I am very interested in your work, and want to study your work well, if you are convenient, can you send me the code related to t-SNE visualization in your work? My mailbox is [email protected], I am grateful!
As anyone would expect after more than a year, the requirements have changed.
In particular, for the Stanford CoreNLP it is not possible to use the 3.9.1 release, as this would rise an error in the odee_preprocess.py
: edu.stanford.nlp.time.TimeExpressionExtractorImpl
Before Java 11, adding --add-modules java.se.ee
to the java command would have fixed the issue. Since Java 9, they stopped including by default some modules, so you need to tell it to use the java.se.ee stuff.
However, the java.se.ee module
is no longer available in Java 11.
After Java 11, the issue has been resolved using the CoreNLP's 3.9.2 release.
I haven't the ace2005 dataset
Some of the issues you might face in running this repository and related fixes [UPDATED to 2021/02]:
_small_
model with output size 128 (otherwise, it will rise a dimensionality issue);calinski_harabaz_score
should be changed into calinski_harabasz_score
您好,阅读了你们的论文,我对论文的领域和无监督方法很感兴趣,也感谢你们开源的代码。但是在复现结果时我发现代码中缺少一部分评价代码(包括t-SNE可视化和Schema Matching等),以及缺少推断出最终结果的代码(类似于测试集中key.txt的结果)。另外,按照slot-coherence中的测试代码,我在基本收敛的模型和全量数据集上运行得到的指标(average topic coherence)只有7%左右(对比论文中18%),以我的理解从answer文件获取key.txt的结果也没有想象中好。请问能否公开一下有关的代码,并指出一下我在复现中可能存在的问题。我的邮箱是[email protected],若能得到回复我不胜感激。
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.