Comments (5)
Hi @ditingdapeng, thanks for your interest in our work!
Sorry, I'm not sure about which issue (or email?) you are mentioning... Would you give me more information about the how many tf-idf need to be kept at the beginning
? Is it about the document filtering process in the inference time or the number of negative examples during training?
from learning_to_retrieve_reasoning_paths.
Thank you for your reply. What I want to express is: In your paper, the first jump from the question to the relevant facts is calculated by the tf-idf method. So when using tf-idf to sort supporting documents, how many paragraphs are selected last as the initial nodes of multi-hop? Hope i can express my problem clearly
from learning_to_retrieve_reasoning_paths.
Thanks for the clarification!
For our best models, we set the initial retrieval number (F
in the paper) to 500, 100, and 100 paragraphs for HotpotQA full wiki, SQuAD Open, and Natural Questions Open, respectively ("Implementation details" section in our paper).
Please see the detailed discussion on the relationship between the number of the initial TF-IDF and performance in Section C.1 & Figure 5 in Appendix.
from learning_to_retrieve_reasoning_paths.
Thank you for your kind reply!
from learning_to_retrieve_reasoning_paths.
You're welcome! Feel free to start another issue or reach me via email if you have follow-up questions.
from learning_to_retrieve_reasoning_paths.
Related Issues (20)
- Some details regarding generating NQ trainset for the reader model HOT 6
- demo.py arg error about NQ HOT 4
- Inconsistent 'answers' types in the nq_reader_train data HOT 1
- `database is locked` while evaluation HOT 1
- How to evaluate the pretrained graph retriever model? HOT 5
- The error when training the graph_retriever in the HotpotQA HOT 5
- Training data construction for reader verifier HOT 3
- json.decoder.JSONDecodeError: Expecting value: line 1 column 1 (char 0) HOT 1
- Fine-tuning on own documents? HOT 2
- What the TF-IDF retriever data output mean HOT 3
- A problem about total tranining steps of reader HOT 2
- How to evaluate the supporting facts in the HotPotQA experiment? HOT 5
- The hyperparameters for training the bert-base reader ? HOT 1
- How to train and evaluate the models in HotpotQA distractor setting? HOT 2
- What do output_masks do? HOT 2
- Why are some document titles missing? HOT 2
- sqlite3.OperationalError: unable to open database file HOT 1
- Why are some document titles missing?
- What is the problem?
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 learning_to_retrieve_reasoning_paths.