Comments (6)
You need to:
1 - add the new document to data/bidaf/shared.json;
2 - start the environment;
3 - query the environment using the doc id of the newly added document:
environment_fn = environment_client.make_environment_reward_fn(
FLAGS.environment_server_address)
f1_scores, _, answers = environment_fn(["Why the sky is blue?"], ["new doc id"])
from active-qa.
But data/bidaf/shared.json contains:
char2idx, word2idx. It doesn't have any parapgraphs.
Do you mean data/squad/shared_dev.json / shared_train.json ?
which are generated by running the preprocess code.
from active-qa.
Sorry, that is right, shared_train.json and shared_dev.json are the ones you need to modify.
from active-qa.
I have added the document(paragraph), word tokens, character tokens of the words to the shared_train.json, shared_dev.json. Previously there are 12635 documents. Now there are 12636 documents. So i queried the bidaf environment with 12635 id. It is showing the following error.
from active-qa.
@rodrigonogueira4 I have run the reformulator with the given checkpoints and now I am also trying to get answers from my custom document. Please if you could explain in detail how to convert custom data into squad data set format and the following steps to get the answers.
from active-qa.
Hello,
@rodrigonogueira4 @graviraja could you please tell me how to run the reformulator? I was able to run the demo.py file, but it just gives the answers to questions using bidaf environment server.
Thanks
from active-qa.
Related Issues (20)
- odd gprc status reporting during selector training HOT 2
- ImportError: cannot import name 'aqa_pb2' HOT 8
- Getting a a grpc.FutureTimeoutError while using Reformulator from the checkpoint HOT 2
- Nonsensical reformed queries from Reformulator HOT 1
- Model pretrained on UN and Paralex datasets
- Are you running the environment server before running the reformulator code? HOT 10
- Getting a grpc.FutureTimeoutError while using Reformulator from the checkpoint HOT 1
- ValueError from the run environment step
- Have not found Monte Carlo Sampling in the code HOT 3
- Setup on Windows
- Docker Image?
- Installation Error
- Assertion Error
- The Process is killed in the middle
- Getting an error while running the reformulator_training file
- How to test with own txt file or a document file
- Problem in download of reformulator pretrained model. HOT 3
- Problem in download the selector pretrained model.
- reformulator and selector links are invalid HOT 2
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
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.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from active-qa.