jp-parallel-gloss makes predictions on similarity of Japanese-to-English glosses (definitions).
This model is fine-tuned using a dataset of over 550,000 parallel/non-parallel gloss pairs from the JMDict database and antonym/synonym pairs from WordNet. The base model used is cross-encoder/ms-macro-MiniLM-L-6-v2.
This model is intended to be used as a CrossEncoder model with sigmoid activation.
from sentence_transformers import CrossEncoder
from torch import nn
model = CrossEncoder("nphach/jp-parallel-gloss", default_activation_function=nn.Sigmoid())
similarity = model.predict(['translation', 'meaning of a word in another language'])
See its application in Kotoba Tag.
- Downloads last month
- 239
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
HF Inference API was unable to determine this model's library.
Model tree for nphach/jp-parallel-gloss
Base model
cross-encoder/ms-marco-MiniLM-L-6-v2