dataiku / dataiku/kiji-proxy

Switch to XLM-RoBERTa for Asian language support

Open
#457 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

advanced Mentoring will be provided
Dominant language
Go
Stars
432
Forks
51
PR merge metrics
No merged PRs in 30d

Description

Motivation

To improve support for Asian languages, we should switch our current model to XLM-RoBERTa.

XLM-RoBERTa is a multilingual model pre-trained on 100 languages, including a wide range of Asian languages (Chinese, Japanese, Korean, Thai, Vietnamese, Hindi, etc.), and consistently outperforms multilingual BERT (mBERT) on cross-lingual benchmarks.

Proposal

  • Evaluate XLM-RoBERTa (xlm-roberta-base and/or xlm-roberta-large) as a replacement for the current model.
  • Benchmark performance on Asian language inputs against the current setup.
  • Update the model loading / inference code paths to support XLM-RoBERTa.
  • Update documentation and any related configs.

References

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by locating the current model loading and inference code paths and related configs, then read how the existing model is benchmarked on language inputs. Evaluate xlm-roberta-base and/or xlm-roberta-large against the current setup. Done means benchmark results are available and the selected model is supported in inference, documentation, and related configs.

Written by the indexing model from the issue text.

Assessment

Tech stack
go, huggingface
Domain
internationalization, machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Quiet
Clarity
Needs clarification
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.