@InProceedings{komiya-shinnou:2018:W18-34,
  author    = {Komiya, Kanako  and  Shinnou, Hiroyuki},
  title     = {Investigating Effective Parameters for Fine-tuning of Word Embeddings Using Only a Small Corpus},
  booktitle = {Proceedings of the Workshop on Deep Learning Approaches for Low-Resource NLP},
  month     = {July},
  year      = {2018},
  address   = {Melbourne},
  publisher = {Association for Computational Linguistics},
  pages     = {60--67},
  abstract  = {Fine-tuning is a popular method to achieve better performance when only a small target corpus is available. However, it requires tuning of a number of metaparameters and thus it might carry risk of adverse effect when inappropriate metaparameters are used. Therefore, we investigate effective parameters for fine-tuning when only a small target corpus is available. In the current study, we target at improving Japanese word embeddings created from a huge corpus. First, we demonstrate that even the word embeddings created from the huge corpus are affected by domain shift. After that, we investigate effective parameters for fine-tuning of the word embeddings using a small target corpus. We used perplexity of a language model obtained from a Long Short-Term Memory network to assess the word embeddings input into the network. 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. In addition, we confirmed that effect of fine-tuning is higher when size of a target corpus was larger.},
  url       = {http://www.aclweb.org/anthology/W18-3408}
}