eugene-yang's picture
git update readme
aaf6c46
---
language:
- en
- fa
tags:
- clir
- colbertx
- plaidx
- xlm-roberta-large
datasets:
- ms_marco
- hltcoe/tdist-msmarco-scores
task_categories:
- text-retrieval
- information-retrieval
task_ids:
- passage-retrieval
- cross-language-retrieval
license: mit
---
# ColBERT-X for English-Persian CLIR using Translate-Distill
## CLIR Model Setting
- Query language: English
- Query length: 32 token max
- Document language: Persian
- Document length: 180 token max (please use MaxP to aggregate the passage score if needed)
## Model Description
Translate-Distill is a training technique that produces state-of-the-art CLIR dense retrieval model through translation and distillation.
`plaidx-large-fas-tdist-mt5xxl-fasfas` is trained with KL-Divergence from the mt5xxl MonoT5 reranker inferenced on
Persian translated MS MARCO training queries and Persian translated passages.
### Teacher Models:
- `t53b`: [`castorini/monot5-3b-msmarco-10k`](https://huggingface.co/castorini/monot5-3b-msmarco-10k)
- `mt5xxl`: [`unicamp-dl/mt5-13b-mmarco-100k`](https://huggingface.co/unicamp-dl/mt5-13b-mmarco-100k)
### Training Parameters
- learning rate: 5e-6
- update steps: 200,000
- nway (number of passages per query): 6 (randomly selected from 50)
- per device batch size (number of query-passage set): 8
- training GPU: 8 NVIDIA V100 with 32 GB memory
## Usage
To properly load ColBERT-X models from Huggingface Hub, please use the following version of PLAID-X.
```bash
pip install PLAID-X==0.3.1
```
Following code snippet loads the model through Huggingface API.
```python
from colbert.modeling.checkpoint import Checkpoint
from colbert.infra import ColBERTConfig
Checkpoint('hltcoe/plaidx-large-fas-tdist-mt5xxl-fasfas', colbert_config=ColBERTConfig())
```
For full tutorial, please refer to the [PLAID-X Jupyter Notebook](https://colab.research.google.com/github/hltcoe/clir-tutorial/blob/main/notebooks/clir_tutorial_plaidx.ipynb),
which is part of the [SIGIR 2023 CLIR Tutorial](https://github.com/hltcoe/clir-tutorial).
## BibTeX entry and Citation Info
Please cite the following two papers if you use the model.
```bibtex
@inproceedings{colbert-x,
author = {Suraj Nair and Eugene Yang and Dawn Lawrie and Kevin Duh and Paul McNamee and Kenton Murray and James Mayfield and Douglas W. Oard},
title = {Transfer Learning Approaches for Building Cross-Language Dense Retrieval Models},
booktitle = {Proceedings of the 44th European Conference on Information Retrieval (ECIR)},
year = {2022},
url = {https://arxiv.org/abs/2201.08471}
}
```
```bibtex
@inproceedings{translate-distill,
author = {Eugene Yang and Dawn Lawrie and James Mayfield and Douglas W. Oard and Scott Miller},
title = {Translate-Distill: Learning Cross-Language Dense Retrieval by Translation and Distillation},
booktitle = {Proceedings of the 46th European Conference on Information Retrieval (ECIR)},
year = {2024},
url = {https://arxiv.org/abs/2401.04810}
}
```