-
Notifications
You must be signed in to change notification settings - Fork 109
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Bug in indexing dev set examples UD POS #25
Comments
@blazejdolicki The *.idx files actually record the original sentence index in the Current models can only make tag predictions for sequences with a maximum length such as 512. In our paper, we used 128 as the maximum length. So to make tag predictions for a longer tokenized sentence, we break it into two for separate predictions, and record their original index in order to merge the two predicted tag sequences as the final output. In your above example, you can check Line 13067 of the original file in Let me know if the above explanation is clean to you. |
Thank you for clarification! So I used the file |
Something is wrong with indexing examples in the dev set of the POS tagging task. In this file every index is assigned to one sentence. However, we can see that index 772 is assigned to two sentences
![image](https://user-images.githubusercontent.com/29718307/81682513-2ad5b100-9455-11ea-9cc6-3bc6f0e83203.png)
This results in predictions of two separate sentences being merged together, like in the following table, which ruins the alignment between sentence and its prediction. You can see that the higlighted ending in row 772 should actually be in the next row.
![image](https://user-images.githubusercontent.com/29718307/81682846-8c961b00-9455-11ea-9bbb-bde7bbf9989c.png)
Row 772 is an example, but there are two more such erroneous rows.
The text was updated successfully, but these errors were encountered: