baidu / baidu/knowledge-driven-dialogue

retrieval_pt baseline中,请问训练时的负样本和预测时的candidates如何构建?

Open
#6 1 comment 0 reactions 0 assignees View on GitHub
Dominant language
Python
Stars
269
Forks
86
PR merge metrics
No merged PRs in 30d

Description

This issue has no description.

Contributor guide

No contributing guide indexed for this repository

Research direction

The issue names the retrieval_pt baseline but provides no body, file paths, or tests. Locate the retrieval_pt training and prediction entry points, trace how negative samples and candidates are built, and document both processes with enough detail to answer the question.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Documentation
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
15/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.