Comments (2)
Hi @mayankpathaklumiq
Thanks for writing. The concept of answerability is that given a query and a paragraph (context passage), determine where that query can be answered from given passage or not. Hence, the input is query, passage and label. Label is 0 (not-answerable) and 1 (for answerable). Similarly, the output produced will either be 0 or 1 while inferring on trained model.
This is mentioned in the answerability example as well, which transforms the MSMARCO data for this task.
After running the transformations part in above example, you can go to the data
directory and checkout the created data files - msmarco_answerability_dev.tsv
(or train/test) to know how is the final input data.
PS. There was minor documentation error in the example in the transformation part which has been corrected.
from multi-task-nlp.
from multi-task-nlp.
Related Issues (11)
- model are not created HOT 1
- torch==1.2.0 not supported
- error in evalution for sentiment task
- What is format of tsv file
- Creating Multi-label Classification Task
- Docs for inferPipeline is incomplete and difficult to understand how to use
- Is this support for hyperparameters tuning? HOT 3
- "snips_intent_ner_to_tsv" : snips_intent_ner_to_tsv, NameError: name 'snips_intent_ner_to_tsv' is not defined HOT 1
- can you mention the server configuration to train the model more specifically answerability detection
- answerability_detection model alwasy predict same class
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 multi-task-nlp.