canjiali/PARADE
code and data to faciliate BERT/ELECTRA for document ranking. Details refer to the paper - PARADE: Passage Representation Aggregation for Document Reranking.
This tool helps information retrieval researchers improve the relevance of search results for a given query. It takes an initial list of documents (and their content) retrieved by a search engine and a user query, then re-ranks the documents to provide a more accurate and useful ordering. Information retrieval scientists and researchers working on search relevance would find this useful.
No commits in the last 6 months.
Use this if you need to significantly improve the ranking quality of documents returned by an existing search engine for specific queries.
Not ideal if you are looking for a standalone search engine or a solution for highly specialized data that differs greatly from general document collections.
Stars
96
Forks
10
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 25, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/canjiali/PARADE"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
yuanzhoulvpi2017/DocumentSearch
基于sentence transformers和chatglm实现的文档搜索工具
IAmPara0x/Yuno
Yuno is context based search engine for anime.
gentaiscool/miners
MINERS ⛏️: The semantic retrieval benchmark for evaluating multilingual language models. (EMNLP...
D-Roberts/transformers-retrieval-ranking-nli-ECIR2021
Multilingual retrieval, ranking and natural language inference with transformers (mBERT);...
atapour/rank-over-class
Source code for the training pipeline of the text ranking model used in the paper entitled "Rank...