sunyilgdx / sifrank Goto Github PK
View Code? Open in Web Editor NEWThe code of our paper "SIFRank: A New Baseline for Unsupervised Keyphrase Extraction Based on Pre-trained Language Model"
The code of our paper "SIFRank: A New Baseline for Unsupervised Keyphrase Extraction Based on Pre-trained Language Model"
Thank you for great work!
However, your paper said using macro F1 score. But i know real implementation is micro avg f1 score not macro.
Isn't right macro needs average f1 score each document?
Line 120 in 274d84b
Hi.
Thank you for the great work. I have one question that I hope you could help with.
In the original Embedrank paper, the variant EmbedRank d2v achieved an F1-score of 31.51 in the Inspec dataset (with N = 5). But your paper reported that it only achieved an F1-score of 27.20. Why is there such a difference? Did you run the original code of Embedrank and it only gave an F1-score of 27.20?
Thanks.
Hi Sun Yi,
thank you for sharing your valuable work. I have run the evaluation myself and the results I obtain slightly differ from the ones in your paper.
Below are the evaluation results for SIFRank on the SemEval2017 dataset.
N=5
P=0.4864097363083164
R=0.14057920037519053
F1=0.21811897398581043
N=10
P=0.43448275862068964
R=0.25114315863524445
F1=0.31830002228991755
N=15
P=0.39143979412163077
R=0.3388439441904092
F1=0.3632478632478633
totally cost 501.45456099510193
Could you explain what might be the reason?
Best regards,
Charles
Hi.
Thanks for your great work.
I check the paper which proposed EmbedRank, they use two different ways to generate the embedding: Sent2vec and Doc2vec. I find that the results of EmbedRank Sent2vec are better than Doc2vec on some datasets.
Did you compare EmbedRank Sent2vec on the SemEval2017 dataset?
Thanks
Kawamura
您好,非常感谢您的工作。近期通过替换 SIFRank中的elmo预训练模型(例如electra,bert),做了一些对比实践,但发现差距较大,不知道什么原因。其次如果其他的预训练模型的确表现不如传统的Elmo,那SIFRank方法进一步提升的可能性在什么方面?
Thank you for sharing your code. A quick question: where or how did you get the file enwiki_vocab_min200.txt
? The one that is in the directory auxiliary_data
.
Thank you.
你好,
我复现代码的结果与论文里面不太一样,在Semeval2017上面,elmo L0,lamda=0.6,N=5 的结果是f1@5 20.21, 与论文中22.59有一定差距,有可能是什么原因呢?
Hello, thank you for sharing your code. I am trying to run your code, and am stuck in the Usage
section in the following line of code:
en_model = StanfordCoreNLP(‘stanford-corenlp-full-2018-02-27',quiet=True)
The code simply 'hangs' or gets stuck in this line and does not move forward. The execution of this line does not finish even after waiting for a few hours. Can you please provide any help with this? Thank you
Hello!
I try to install SIFRank, but I have error:
"No module named 'allennlp.commands.elmo'"
Do you know, what can I do with it?
I read that the current version of allennlp does not contain the elmo.py file, and whan i try to install previous version, i have error too.
I will be grateful for the help because SIFRank is very interested me.
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.