Git Product home page Git Product logo

attentivepathranking's People

Contributors

wglti avatar wliu88 avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar

attentivepathranking's Issues

predicted path

I wanted to know where I can see the predicted path, do you have a file to save all the predicted paths?

Hard to understand input data during inference

Hi,
I'm really into this repo, but I'm having a hard time understanding the inputs of this model. inputs look like this "tip.n.04,tip.n.04,tip.n.04,tip.n.04,tip.n.04,tip.n.04,tip.n.04,tip.n.04,tip.n.04,tip.n.04,tip.n.04,tip.n.04,tip.n.04,tip.n.04,tip.n.04,south_frigid_zone.n.01,tannoy.n.01", how to explain the repeat "tip.n.04" ? Is this a sub graph of a knowledge graph? And some output path_str also confuse me like "stratum.n.01-hypernym-stratum.n.01-_synset_domain_topic_of-hate.v.01-hypernym-hate.v.01-hypernym-reason.v.03-_hypernym-hate.v.01" while the subject is "synset:rowing.n.01" and object is "synset:feathering.n.01". Much appreciated

Data in the drop box does not match the training file

Hi, recently I have to go through all the steps from PRA to CVSM to understand the training data. It seems the vocab in the drop box data does not fit the training files.
For example:
456,10,9,8092,8092,8092,8092,8092,8092,8092,8092,8092,8092,8092,8092,19020,19 should represent the entity[19020] while [456, 10, 9] represents entity[19020]'s hypernym. But however I found that entity[19020] refers to "synset:range_of_mountains.n.01" and its hypernym should be ["geological_formation.n.01", "object.n.01", "entity.n.01"] which transfer to [1679, 18, 6], so basicly it's a dismatch.
After I run all the preprocess in demo_wn18rr.py, I get the new vocab and training files and the new ones can match.

Failed when running the test of your PRA.

Following your brief introduction of running PRA test, 2 test cases failed out of 159 in total. Do you have any suggestions to solve this problem?

git clone [email protected]:wliu88/pra_scala.git
cd pra_scala
sbt test
[info] ScalaTest
[info] Run completed in 6 seconds, 729 milliseconds.
[info] Total number of tests run: 159
[info] Suites: completed 26, aborted 0
[info] Tests: succeeded 157, failed 2, canceled 0, ignored 0, pending 0
[info] *** 2 TESTS FAILED ***
[error] Failed: Total 183, Failed 2, Errors 0, Passed 181
[error] Failed tests:
[error]         edu.cmu.ml.rtw.pra.features.LexicalizedPathTypeSpec
[error] (test:test) sbt.TestsFailedException: Tests unsuccessful
[error] Total time: 8 s, completed Nov 9, 2020 5:21:35 PM

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– 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. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

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 โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.