Skip to content
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.

Sign up for GitHub

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

Jump to bottom

Add no_answer option to results #24

Merged
merged 6 commits into from
Feb 19, 2020
Merged

Add no_answer option to results #24

Changes from 1 commit
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
58e56b3
add no_answer option to aggregation of paragraphs level preds
tholor Feb 17, 2020
85fbf50
change offsets to FARM default
tholor Feb 17, 2020
dc91883
Add ranking of no ans relative to positive answers
Timoeller Feb 19, 2020
c6d9da8
Add doc for no answer boosting
Timoeller Feb 19, 2020
dface98
Adjust printing of all details
Timoeller Feb 19, 2020
840b368
Add no ans example
Timoeller Feb 19, 2020
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Next Next commit
Add doc for no answer boosting
  • Loading branch information
@Timoeller
Timoeller committed Feb 19, 2020
commit c6d9da8827887b58b413a570d261e2625946f3ed
1 change: 1 addition & 0 deletions tutorials/Tutorial1_Basic_QA_Pipeline.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -37,6 +37,7 @@
# Reader use more powerful but slower deep learning models
# You can select a local model or any of the QA models published on huggingface's model hub (https://huggingface.co/models)
# here: a medium sized BERT QA model trained via FARM on Squad 2.0
# You can adjust the model to return "no answer possible" with the no_ans_boost. Higher values mean the model prefers "no answer possible"
reader = FARMReader(model_name_or_path="deepset/bert-base-cased-squad2", use_gpu=False, no_ans_boost=0)

# OR: use alternatively a reader from huggingface's transformers package (https://github.com/huggingface/transformers)
Expand Down