-
## 一言でいうと
オープンドメインのQAで必要な回答が含まれていそうな文書(Passage)の抽出について、既存のTF-IDFやBM25よりベクトル特徴の内積を使用した抽出の方が1~2割精度が改善するという研究結果。Q、Aは別個のBERTでEncodeされ、実行時は FAISSで近傍ベクトルを抽出する。
### 論文リンク
https://arxiv.org/abs/2004.…
-
- [ ] [README.md · BAAI/bge-reranker-large at main](https://huggingface.co/BAAI/bge-reranker-large/blob/main/README.md?code=true)
# README.md · BAAI/bge-reranker-large at main
## FlagEmbedding
Flag…
-
# Keywords
Contrastive learning, Inverse Cloze Task, MoCo,
# TL;DR
# Abstract
Recently, information retrieval has seen the emergence of dense retrievers, using neural
networks, as an alternativ…
-
# Keywords
In-batch negative training
# TL;DR
Train better dense embedding model using only pairs of questions and passages without additional pretraining.
# Abstract
Open-domain question ans…
-
## Problem statement
1. 적은 양의 (question, passage) pair로 retrieval 성능을 낼 수 있는 training scheme을 찾는다.
2. question과 passage의 내적으로 유사도를 비교할 수 있는 low-dimensional & continuous space에 임베딩한다.
## Baselin…
-
## 一言でいうと
マルチホップのQA(HotpotQAなど)で、再帰的なクエリにより高い精度を記録した研究。Query/PassageそれぞれにEncodeして内積により近さを取り抽出するのが基本だが、QueryのEncode対象に抽出結果をどんどん加えていく。
### 論文リンク
https://arxiv.org/abs/2009.12756
### 著者/所属機関
…
-
Hi everyone.
I'm implementing a multitask model to predict the next item in the basket.
In my candidate model, I would like to insert a feature that represents the score (likelihood) between the…
-
Hi @maciejkula thanks again for a great library!
I have another question which is a little theoretical, I would like to understand how to handle negative examples explicitly in this library. So as …
-
请问该如何把三种检索混合在一起使用?
-
### Question Validation
- [X] I have searched both the documentation and discord for an answer.
### Question
Hi, I have a (typical) use-case where vector index mostly works, but there are tim…