1 |
『現代日本語書き言葉均衡コーパス』出版書籍サンプルのNDC別語彙分布
|
|
|
|
In: https://ccd.ninjal.ac.jp/lrw2021.html (2021)
|
|
BASE
|
|
Show details
|
|
5 |
ALICE++ : Adversarial Training for Robust and Effective Temporal Reasoning
|
|
|
|
BASE
|
|
Show details
|
|
7 |
The Annotation of Antonym Information in the 'Word List by Semantic Principles'
|
|
|
|
BASE
|
|
Show details
|
|
8 |
『現代日本語書き言葉均衡コーパス』新聞記事情報を用いたジャンル別語彙分布
|
|
|
|
In: https://ccd.ninjal.ac.jp/lrw2021.html (2021)
|
|
BASE
|
|
Show details
|
|
10 |
自然言語処理 : 言語資源・意味解析(レクチャーシリーズ「人工知能の今」第6回)
|
|
|
|
In: https://www.ai-gakkai.or.jp/vol35_no1/ (2020)
|
|
BASE
|
|
Show details
|
|
11 |
Design of BCCWJ-EEG : Balanced Corpus with Human Electroencephalography
|
|
|
|
BASE
|
|
Show details
|
|
12 |
KOTONOHA : A Corpus Concordance System for Skewer-Searching NINJAL Corpora
|
|
|
|
BASE
|
|
Show details
|
|
15 |
Composing Word Vectors for Japanese Compound Words Using Bilingual Word Embeddings
|
|
|
|
BASE
|
|
Show details
|
|
16 |
Generation and Evaluation of Concept Embeddings Via Fine-Tuning Using Automatically Tagged Corpus
|
|
|
|
BASE
|
|
Show details
|
|
17 |
編集後記
|
|
|
|
In: https://pj.ninjal.ac.jp/corpus_center/lrw2020.html (2020)
|
|
BASE
|
|
Show details
|
|
18 |
Automatic Creation of Correspondence Table of Meaning Tags from Two Dictionaries in One Language Using Bilingual Word Embedding
|
|
|
|
Abstract:
Ibaraki University ; Ibaraki University ; National Institute for Japanese Language and Linguistics ; Ibaraki University ; 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.
|
|
Keyword:
Bilingual Word Embedding; Concept Embeddings; Dictionary; Word Embeddings
|
|
URL: https://repository.ninjal.ac.jp/?action=repository_action_common_download&item_id=3085&item_no=1&attribute_id=22&file_no=1 https://repository.ninjal.ac.jp/?action=repository_uri&item_id=3085 http://id.nii.ac.jp/1328/00003069/
|
|
BASE
|
|
Hide details
|
|
20 |
Dynamically Updating Event Representations for Temporal Relation Classification with Multi-category Learning
|
|
|
|
BASE
|
|
Show details
|
|
|
|