|
Microsoft Research WikiQA Code Package |
We are releasing the code of some models used in our EMNLP-2015 paper, “WikiQA: A Challenge Dataset for Open-Domain Question Answering.” The code includes implementation of two models: Convolutional Neural Networks (CNN), and Logistic regression with CNN and count features (CNN-Cnt). Last published: October 30, 2015.
We are releasing the code of some models used in our EMNLP-2015 paper, “WikiQA: A Challenge Dataset for Open-Domain Question Answering.” The code includes implementation of two models: Convolutional Neural Networks (CNN), and Logistic regression with CNN and count features (CNN-Cnt). The models intend to judge whether a given sentence can be used to answer the input question. Please refer to the README.txt file in the download and also the paper for detail.
Files
|
Status: LiveThis download is still available on microsoft.com. The downloads below will come directly from the Microsoft Download Center. |
| Files |
|---|
WikiQACodePackage.zip
|
System Requirements
Operating Systems: Windows 10, Windows 7, Windows 8
- Windows 7, Windows 8, or Windows 10
Installation Instructions
- Click Download and follow the instructions.