phongnt570 / ascent Goto Github PK
View Code? Open in Web Editor NEWAdvanced Semantics for Commonsense Knowledge Extraction (WWW 2021)
Home Page: https://ascent.mpi-inf.mpg.de
License: Apache License 2.0
Advanced Semantics for Commonsense Knowledge Extraction (WWW 2021)
Home Page: https://ascent.mpi-inf.mpg.de
License: Apache License 2.0
Hi @phongnt570 ! This is a great library. I'd like to use it in the BigScience workshop. https://github.com/bigscience-workshop Would it be possible to release this code as Apache 2.0?
I installed and tried the project, but it seems it doesn't generate any output, instead, it says there is no output file.
Enter subjects: pen.n.01
[18615] [23-04 12:57:05] [__main__] [INFO] Running pipeline for 1 subjects: [pen.n.01]
[0] Bing Search
[1] Crawl articles
[2] Filter irrelevant articles
[3] Extract knowledge
[4] Cluster similar triples
[5] Label facets
[6] Group similar facets
From module: 0
To module: 1
[18668] [23-04 12:57:09] [pipeline.bing_search_module] [INFO] Subject pen.n.01 - Bing search
[18668] [23-04 12:57:09] [retrieval.bing_search] [INFO] Subject pen.n.01 - Search query: `what is pen?`
[18668] [23-04 12:57:10] [retrieval.bing_search] [INFO] Detected manual WordNet-Wikipedia linking
[18668] [23-04 12:57:10] [pipeline.bing_search_module] [CRITICAL] pen.n.01, list assignment index out of range
[18615] [23-04 12:57:10] [pipeline.article_grab_module] [INFO] Subject pen.n.01 - Crawl relevant articles
[18615] [23-04 12:57:10] [pipeline.article_grab_module] [CRITICAL] pen.n.01, [Errno 2] No such file or directory: '../output/url/pen.n.01.txt'
what does the following line do?
ascent/src/pipeline/pipeline.py", line 41, in <listcomp>
[wn.synset(subject) for subject in subject_list]
It can generate the following error for some words, which are absent.
Traceback (most recent call last):
File "main.py", line 73, in <module>
pipeline.run(subject_list=subject_list, from_module=from_module, to_module=to_module)
File "/home/pouramini/ascent/src/pipeline/pipeline.py", line 41, in run
[wn.synset(subject) for subject in subject_list]
File "/home/pouramini/ascent/src/pipeline/pipeline.py", line 41, in <listcomp>
[wn.synset(subject) for subject in subject_list]
File "/home/pouramini/miniconda3/lib/python3.7/site-packages/nltk/corpus/reader/wordnet.py", line 1329, in synset
raise WordNetError(message % (lemma, pos))
nltk.corpus.reader.wordnet.WordNetError: no lemma 'آزمایش' with part of speech 'n'
Anyways, I had some general questions and would be grateful if you guide me.
If I want to use this package for another language (in my case Persian) which modules do you think I must change? How can I connect it to BabelNet or another resource instead of English WordNet? Is WordNet a required step? Also what wn_wp_map.csv
do?
I must study the associated paper more, and I may modify my questions, but if you already have some guides please let me know.
I also managed to use Google Search instead of Bing search. If you are interested, I could give you the code.
Hello, I'm really interested in the part related to Extrinsic Evaluation in your paper. I read the papers you cited, but some details are still unclear. For example, how to convert assertions to natural language (which are used as context); or some other the training details in this project. Could you provide the code or some other related projects ? Maybe LAMA is a good start?
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.