MTEB logo MTEB
retrieval text

CodeTransOceanDL

Cite this task

@misc{yan2023codetransoceancomprehensivemultilingualbenchmark,
  archiveprefix = {arXiv},
  author = {Weixiang Yan and Yuchen Tian and Yunzhe Li and Qian Chen and Wen Wang},
  eprint = {2310.04951},
  primaryclass = {cs.AI},
  title = {CodeTransOcean: A Comprehensive Multilingual Benchmark for Code Translation},
  url = {https://arxiv.org/abs/2310.04951},
  year = {2023},
}

The dataset is a collection of equivalent Python Deep Learning code snippets written in different machine learning framework. The task is to retrieve the equivalent code snippet in another framework, given a query code snippet from one framework.

Domains: ProgrammingWritten
Languages: python
Task type
Retrieval
Main metric
ndcg_at_10
License
apache-2.0
Dates
2023-10-08 → 2023-10-08
Annotations
derived
Sample creation
found
Models scored …
Dataset preview CoIR-Retrieval/codetrans-dl Open on HuggingFace →

Model scores

Loading…