Kanako Komiya


2020

pdf bib
Automatic Creation of Correspondence Table of Meaning Tags from Two Dictionaries in One Language Using Bilingual Word Embedding
Teruo Hirabayashi | Kanako Komiya | Masayuki Asahara | Hiroyuki Shinnou
Proceedings of the 13th Workshop on Building and Using Comparable Corpora

In this paper, we show how to use bilingual word embeddings (BWE) to automatically create a corresponding table of meaning tags from two dictionaries in one language and examine the effectiveness of the method. To do this, we had a problem: the meaning tags do not always correspond one-to-one because the granularities of the word senses and the concepts are different from each other. Therefore, we regarded the concept tag that corresponds to a word sense the most as the correct concept tag corresponding the word sense. We used two BWE methods, a linear transformation matrix and VecMap. We evaluated the most frequent sense (MFS) method and the corpus concatenation method for comparison. The accuracies of the proposed methods were higher than the accuracy of the random baseline but lower than those of the MFS and corpus concatenation methods. 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. Also, our methods could be performed when we have only concept or word sense embeddings whereas the MFS method requires a parallel corpus and the corpus concatenation method needs two tagged corpora.

2018

pdf bib
All-words Word Sense Disambiguation Using Concept Embeddings
Rui Suzuki | Kanako Komiya | Masayuki Asahara | Minoru Sasaki | Hiroyuki Shinnou
Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)

pdf bib
Investigating Effective Parameters for Fine-tuning of Word Embeddings Using Only a Small Corpus
Kanako Komiya | Hiroyuki Shinnou
Proceedings of the Workshop on Deep Learning Approaches for Low-Resource NLP

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.

pdf bib
Domain Adaptation for Sentiment Analysis using Keywords in the Target Domain as the Learning Weight
Jing Bai | Hiroyuki Shinnou | Kanako Komiya
Proceedings of the 32nd Pacific Asia Conference on Language, Information and Computation

pdf bib
Domain Adaptation Using a Combination of Multiple Embeddings for Sentiment Analysis
Hiroyuki Shinnou | Xinyu Zhao | Kanako Komiya
Proceedings of the 32nd Pacific Asia Conference on Language, Information and Computation

pdf bib
Fine-tuning for Named Entity Recognition Using Part-of-Speech Tagging
Masaya Suzuki | Kanako Komiya | Minoru Sasaki | Hiroyuki Shinnou
Proceedings of the 32nd Pacific Asia Conference on Language, Information and Computation

2017

pdf bib
Japanese all-words WSD system using the Kyoto Text Analysis ToolKit
Hiroyuki Shinnou | Kanako Komiya | Minoru Sasaki | Shinsuke Mori
Proceedings of the 31st Pacific Asia Conference on Language, Information and Computation

2016

pdf bib
Comparison of Annotating Methods for Named Entity Corpora
Kanako Komiya | Masaya Suzuki | Tomoya Iwakura | Minoru Sasaki | Hiroyuki Shinnou
Proceedings of the 10th Linguistic Annotation Workshop held in conjunction with ACL 2016 (LAW-X 2016)

pdf bib
Constructing a Japanese Basic Named Entity Corpus of Various Genres
Tomoya Iwakura | Kanako Komiya | Ryuichi Tachibana
Proceedings of the Sixth Named Entity Workshop

pdf bib
Supervised Word Sense Disambiguation with Sentences Similarities from Context Word Embeddings
Shoma Yamaki | Hiroyuki Shinnou | Kanako Komiya | Minoru Sasaki
Proceedings of the 30th Pacific Asia Conference on Language, Information and Computation: Oral Papers

2015

pdf bib
Domain Adaptation with Filtering for Named Entity Extraction of Japanese Anime-Related Words
Kanako Komiya | Daichi Edamura | Ryuta Tamura | Minoru Sasaki | Hiroyuki Shinnou | Yoshiyuki Kotani
Proceedings of the International Conference Recent Advances in Natural Language Processing

pdf bib
Surrounding Word Sense Model for Japanese All-words Word Sense Disambiguation
Kanako Komiya | Yuto Sasaki | Hajime Morita | Minoru Sasaki | Hiroyuki Shinnou | Yoshiyuki Kotani
Proceedings of the 29th Pacific Asia Conference on Language, Information and Computation

pdf bib
Hybrid Method of Semi-supervised Learning and Feature Weighted Learning for Domain Adaptation of Document Classification
Hiroyuki Shinnou | Liying Xiao | Minoru Sasaki | Kanako Komiya
Proceedings of the 29th Pacific Asia Conference on Language, Information and Computation

pdf bib
Learning under Covariate Shift for Domain Adaptation for Word Sense Disambiguation
Hiroyuki Shinnou | Minoru Sasaki | Kanako Komiya
Proceedings of the 29th Pacific Asia Conference on Language, Information and Computation: Posters

pdf bib
Unsupervised Domain Adaptation for Word Sense Disambiguation using Stacked Denoising Autoencoder
Kazuhei Kouno | Hiroyuki Shinnou | Minoru Sasaki | Kanako Komiya
Proceedings of the 29th Pacific Asia Conference on Language, Information and Computation: Posters

2012

pdf bib
Automatic Domain Adaptation for Word Sense Disambiguation Based on Comparison of Multiple Classifiers
Kanako Komiya | Manabu Okumura
Proceedings of the 26th Pacific Asia Conference on Language, Information, and Computation

pdf bib
The Transliteration from Alphabet Queries to Japanese Product Names
Rieko Tsuji | Yoshinori Nemoto | Wimvipa Luangpiensamut | Yuji Abe | Takeshi Kimura | Kanako Komiya | Koji Fujimoto | Yoshiyuki Kotani
Proceedings of the 26th Pacific Asia Conference on Language, Information, and Computation

2011

pdf bib
Negation Naive Bayes for Categorization of Product Pages on the Web
Kanako Komiya | Naoto Sato | Koji Fujimoto | Yoshiyuki Kotani
Proceedings of the International Conference Recent Advances in Natural Language Processing 2011

pdf bib
Automatic Determination of a Domain Adaptation Method for Word Sense Disambiguation Using Decision Tree Learning
Kanako Komiya | Manabu Okumura
Proceedings of 5th International Joint Conference on Natural Language Processing

2010

pdf bib
SemEval-2010 Task: Japanese WSD
Manabu Okumura | Kiyoaki Shirai | Kanako Komiya | Hikaru Yokono
Proceedings of the 5th International Workshop on Semantic Evaluation