Comments (2)
dhdhagar
commented on May 20, 2024
1
That makes it clear, thank you! So, --top_k is used to fetch a larger number of phrases, and the length of the final results depends on --psg_top_k.
from densephrases.
jhyuklee
commented on May 20, 2024
Hi @dhdhagar! Thanks for your issue.
In this makefile line:
Line 490 in 3a0365e
you can see that we are retrieving top 200 phrases first. And the aggregation based on the unique passages happen here:
https://github.com/princeton-nlp/DensePhrases/blob/main/densephrases/index.py#L430
For our current datasets provided, this is enough to ensure outputting 100 passages per query. There are a very small number of edge cases where top 100 passages are not retrieved even with this setting, and you can enlarge the top-k to 400 in the makefile. Currently there's no automatic procedure for this.
from densephrases.
Related Issues (20)
- Issue while creating faiss index, Command is not clear HOT 14
- How to extract phrases from Wikipedia? HOT 5
- Representations of phrases HOT 6
- Train custom teacher model HOT 3
- Question about faiss parameter HOT 4
- Modifying num_clusters in index-vecs HOT 11
- Unable to Reproduce Passage Retrieval Results on NQ HOT 9
- Reproduction of DensePhrase (w/ PQ, w/o qft) on SQuAD HOT 9
- Significance of line 174 in train_query.py code HOT 4
- failed with "make draft MODEL_NAME=test" HOT 2
- Where is the code for queries to get phrases searching score rank? HOT 2
- how to evaluate model on SQuAD (non openQA settings) HOT 1
- How to choose phrase to encode in wikipedia document
- DensePhrases for non-answerable questions
- run_demo.py : IndexError: index out of range in self HOT 1
- editing the demo file HOT 3
- IndexError: index 99 is out of bounds for axis 0 with size 35
- Recipe to build dense representations from corpus HOT 1
- Implementation of contrastive loss with in-passage negative
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 densephrases.