|
|
| --- |
| language: |
| - vi |
| - ede |
|
|
| tags: |
| - splade |
| - morpheme-tokenizer |
| - sparse-retrieval |
| - cross-lingual-retrieval |
| - information-retrieval |
| - EViRAL |
| --- |
| |
| # SPLADE + Morpheme Tokenizer — EViRAL |
|
|
| Cross-lingual retrieval model: |
|
|
| Ede query → Vietnamese passage retrieval |
|
|
| ## Architecture |
|
|
| - Backbone: 6-layer Transformer |
| - Retrieval head: SPLADE sparse expansion |
| - Tokenizer: Morpheme tokenizer v4 |
|
|
| ## Files |
|
|
| | File | Description | |
| |---|---| |
| | mlm.pt | MLM pre-trained encoder | |
| | align.pt | Cross-lingual aligned encoder | |
| | finetune.pt | Fine-tuned retrieval encoder | |
|
|
| ## Notes |
|
|
| This model replaces vanilla dense retrieval |
| with SPLADE sparse lexical expansion while |
| keeping the same Transformer backbone. |
|
|
