|
--- |
|
tags: |
|
- text2text-generation |
|
- definition-modeling |
|
metrics: |
|
- rouge |
|
model-index: |
|
- name: mt0-definition-ru-xl |
|
results: [] |
|
language: |
|
- ru |
|
widget: |
|
- text: "Мы сели в тачку и поехали по ресторанам. Что такое тачка?" |
|
example_title: "Definition generation" |
|
license: cc-by-sa-4.0 |
|
--- |
|
|
|
# mT0-Definition-Ru XL |
|
|
|
This model is a version of [mT0 XL](https://huggingface.co/bigscience/mt0-xl) finetuned on the Russian part of [CodWoE](https://aclanthology.org/2022.semeval-1.1/), |
|
a dataset of definitions and usage examples. |
|
|
|
It generates definitions of Russian words in context. |
|
Its input is the usage example and the instruction question "Что такое TARGET_WORD?" |
|
|
|
## Model description |
|
|
|
See details in the paper `Enriching Word Usage Graphs with Cluster Definitions` (LREC-COLING'2024) by |
|
Mariia Fedorova, Andrey Kutuzov, Nikolay Arefyev and Dominik Schlechtweg. |
|
|
|
## Intended uses & limitations |
|
|
|
The model is intended for research purposes, as a source of contextualized dictionary-like lexical definitions. |
|
Generated definitions can contain all sorts of biases and stereotypes, stemming from the underlying language model. |
|
|
|
## Training and evaluation data |
|
|
|
Russian subset of *CodWoE* ([Mickus et al., SemEval 2022](https://aclanthology.org/2022.semeval-1.1/)). |
|
|
|
## Training results |
|
|
|
mT0-Definition-Ru XL achieves the following results on the CodWoE evaluation set: |
|
|
|
- Loss: 1.7996 |
|
- Rouge1: 17.5576 |
|
- Rouge2: 8.7614 |
|
- Rougel: 17.2533 |
|
- Rougelsum: 17.3204 |
|
- Gen Len: 21.6774 |
|
|
|
## Training procedure |
|
|
|
mT0-Definition-Ru XL was fine-tuned in a sequence-to-sequence mode on examples of contextualized dictionary definitions. |
|
|
|
### Training hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
- learning_rate: 5e-05 |
|
- train_batch_size: 4 |
|
- eval_batch_size: 4 |
|
- seed: 42 |
|
- distributed_type: multi-GPU |
|
- num_devices: 8 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 128 |
|
- total_eval_batch_size: 32 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 20.0 |
|
|
|
### Framework versions |
|
|
|
- Transformers 4.37.1 |
|
- Pytorch 1.13.1+rocm5.2 |
|
- Datasets 2.16.1 |
|
- Tokenizers 0.15.1 |
|
|
|
## Citation |
|
|
