Search Results for author:
Found 22 papers, 0 papers with code
Domain-Specific Japanese ELECTRA Model Using a Small Corpus
Herein, we propose a method for addressing the computational efficiency of pretraining models in domain shift by constructing an ELECTRA pretraining model on a Japanese dataset and additional pretraining this model in a downstream task using a corpus from the target domain.
Application of Mix-Up Method in Document Classification Task Using BERT
In an experiment using the livedoor news corpus, which is Japanese, we compared the accuracy of document classification using two methods for selecting documents to be concatenated with that of ordinary document classification.
Automatic Creation of Correspondence Table of Meaning Tags from Two Dictionaries in One Language Using Bilingual Word Embedding
However, because our method utilized the embedding vectors of the word senses, the relations of the sense tags corresponding to concept tags could be examined by mapping the sense embeddings to the vector space of the concept tags.
Investigating Effective Parameters for Fine-tuning of Word Embeddings Using Only a Small Corpus
The experiments revealed that fine-tuning sometimes give adverse effect when only a small target corpus is used and batch size is the most important parameter for fine-tuning.
Detection of Peculiar Word Sense by Distance Metric Learning with Labeled Examples
Then, peculiar examples are extracted using the local outlier factor, which is a density-based outlier detection method, from the updated training and test data.
