| 電子情報通信学会 研究会発表申込システム 講演論文 詳細 |
技報閲覧サービス [ログイン] 技報アーカイブ |
| トップに戻る | 前のページに戻る | [Japanese] / [English] |
| 講演抄録／キーワード | ||
| 講演名 | 2018-07-28 10:00 Improve accuracy of predicting confidential words in juditial precedents ○Masakazu Kanazawa・Atsushi Ito（Utsunomiya Univ.）・Yuya Kiryu（KDDI）・Kazuyuki Yamaswa（TKC）・Takehiko Kasahara（Toin Yokohama Univ.）  TL2018-12 |
|
| 抄録 | （和） | (まだ登録されていません) |
| （英） | The judicial system in which IT technology was introduced is called Cyber Court. In judicial field in Japan, confidential words such as personal names and personal places are converted to meaningless words manually because Japanese values do not allow the disclosure of the individual information. It is not easy to construct a comprehensive dictionary for detecting confidential words. We have already proposed two models that predict confidential words automatically by using neural networks. We used long short-term memory (LSTM) and continuous bag-of-words (CBOW) as our language models. Firstly, we explained the possibility of detecting the words surrounding a confidential word by using CBOW. Then, we proposed two models to predict the confidential words from the neighboring words by applying LSTM. The first model imitates the anonymization work by a human being, and the second model was based on CBOW. The results show that the first model is more effective for predicting confidential words than the simple LSTM model. We expected the second model to have paraphrasing ability to increase the possibility of finding other paraphraseable One is Bi-directional LSTM LR model and the other is Sum-LSTM based on the CBOW model. The two proposed models were effective for predicting all the words. However, only the Bi-directional LSTM LR model was effective for predicting confidential words. This could have happened because Sum-LSTM was based on CBOW. CBOW is an effective model for paraphrasing words; therefore, Sum-LSTM also has that mechanism. Therefore, when Sum-LSTM predicted a word whose answer was “confidential,” the CW_PPL (Confidential word perplexity) became worse because there was a possibility of paraphrasing words of paraphrasing words such as “plaintiff,” “defendant,” “doctor,” and “teacher.” Knowing the paraphrased words of the confidential words meant that the embedding vectors of the confidential words could be successfully generated. This meant that the model could recognize the meaning of “confidential.” However, the prediction accuracy did not improve; therefore, there was a problem in calculating the probability of the prediction task. To solve this problem, we could exclude these paraphraseable words from the choices when calculating the probability. It is also important to examine scores other than PPL. Then we consider to improve accuracy of predicting confidential words. At first we focus the parameter of neural network. We would change the window size to large because we think the surrounding words of the target words (that is window size) is larger, accuracy will be high. Then, we are experimenting but we can’t get the results by now to spent more memory and more calculating time. Next, we would use the proper noun dictionary combined neural network. But we don’t discuss in the this paper. | |
| キーワード | （和） | / / / / / / / |
| （英） | Bi-directional LSTM / CBOW / ppl / cw-ppl / window size / / / | |
| 文献情報 | 信学技報, vol. 118, no. 163, TL2018-12, pp. 1-6, 2018年7月. | |
| 資料番号 | TL2018-12 | |
| 発行日 | 2018-07-21 (TL) | |
| ISSN | Print edition: ISSN 0913-5685 Online edition: ISSN 2432-6380 | |
| 著作権に ついて |
技術研究報告に掲載された論文の著作権は電子情報通信学会に帰属します．(許諾番号：10GA0019/12GB0052/13GB0056/17GB0034/18GB0034) | |
| PDFダウンロード | TL2018-12 |
|
| 研究会情報 | |
| 研究会 | TL |
| 開催期間 | 2018-07-28 - 2018-07-29 |
| 開催地（和） | 慶応大学 |
| 開催地（英） | Keio University |
| テーマ（和） | 人間の言語処理と学習 |
| テーマ（英） | Human Language Processing and Learning |
| 講演論文情報の詳細 | |
| 申込み研究会 | TL |
| 会議コード | 2018-07-TL |
| 本文の言語 | 英語 |
| タイトル（和） | |
| サブタイトル（和） | |
| タイトル（英） | Improve accuracy of predicting confidential words in juditial precedents |
| サブタイトル（英） | |
| キーワード(1)（和/英） | / Bi-directional LSTM |
| キーワード(2)（和/英） | / CBOW |
| キーワード(3)（和/英） | / ppl |
| キーワード(4)（和/英） | / cw-ppl |
| キーワード(5)（和/英） | / window size |
| キーワード(6)（和/英） | / |
| キーワード(7)（和/英） | / |
| キーワード(8)（和/英） | / |
| 第1著者 氏名（和/英/ヨミ） | 金澤 政和 / Masakazu Kanazawa / カナザワ マサカズ |
| 第1著者 所属（和/英） | 宇都宮大学 (略称： 宇都宮大) Utsunomiya University (略称： Utsunomiya Univ.) |
| 第2著者 氏名（和/英/ヨミ） | 伊藤 篤 / Atsushi Ito / イトウ アツシ |
| 第2著者 所属（和/英） | 宇都宮大学 (略称： 宇都宮大) Utsunomiya University (略称： Utsunomiya Univ.) |
| 第3著者 氏名（和/英/ヨミ） | 桐生 雄也 / Yuya Kiryu / キリュウ ユウヤ |
| 第3著者 所属（和/英） | KDDI 株式会社 (略称： KDDI) KDDI Corporation (略称： KDDI) |
| 第4著者 氏名（和/英/ヨミ） | 山澤 和之 / Kazuyuki Yamaswa / ヤマサワ カズユキ |
| 第4著者 所属（和/英） | TKC Corporation (略称： TKC) TKC Corporation (略称： TKC) |
| 第5著者 氏名（和/英/ヨミ） | 笠原 毅彦 / Takehiko Kasahara / カサハラ タケヒコ「 |
| 第5著者 所属（和/英） | 桐蔭横浜大学 (略称： 桐蔭横浜大) Toin Yokohama Univeecity (略称： Toin Yokohama Univ.) |
| 講演者 | 第1著者 |
| 発表日時 | 2018-07-28 10:00:00 |
| 発表時間 | 30分 |
| 申込先研究会 | TL |
| 資料番号 | TL2018-12 |
| 巻番号（vol） | vol.118 |
| 号番号（no） | no.163 |
| ページ範囲 | pp.1-6 |
| ページ数 | 6 |
| 発行日 | 2018-07-21 (TL) |
[研究会発表申込システムのトップページに戻る]