Text Personalization with Automatic Summarization and Text Simplification
| Project/Area Number |
17K12738
|
|---|
| Research Category |
Grant-in-Aid for Young Scientists (B)
|
| Allocation Type | Multi-year Fund |
|---|
| Research Field |
Intelligent informatics
|
|---|
| Research Institution | Tokyo Institute of Technology |
|---|
Principal Investigator |
|
|---|
| Project Period (FY) |
2017-04-01 – 2020-03-31
|
| Project Status |
Completed (Fiscal Year 2019)
|
| Budget Amount *help |
¥4,030,000 (Direct Cost: ¥3,100,000、Indirect Cost: ¥930,000)
Fiscal Year 2019: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2018: ¥780,000 (Direct Cost: ¥600,000、Indirect Cost: ¥180,000)
Fiscal Year 2017: ¥2,600,000 (Direct Cost: ¥2,000,000、Indirect Cost: ¥600,000)
|
|---|
| Keywords | 自動要約 / 文簡約 / 深層学習 / 単一文書要約 / 自然言語処理 |
|---|
| Outline of Final Research Achievements |
We built a text-simplification corpus, and developed a model summarizing and simplifying texts with a large-scale automatic summarization corpus. We summarized and simplified newswire articles with that model. We implemented two models: a model which processed one article sentence-by-sentence, and a model which processed one whole article all at once. Those models were learned with the above corpora. Our quantitative experiments showed that a model that combined the above two models could generate better outputs than the single model did in terms of automatic quantitative evaluation methods such as BLEU, ROUGE, and SARI.
|
| Academic Significance and Societal Importance of the Research Achievements |
情報化社会の進展に伴い，自動要約および平易化といった，テキストの読解を支援する技術への需要が高まっている．長いテキストから重要箇所を抽出し短くまとめる「要約」は読み手の迅速な内容把握を可能にし，大量の文献の読解や調査などを必要とする知識労働者の生産性を大幅に向上せしめることが期待される．また，専門用語などの難解な表現に対し削除及び易しい表現への置換を行う「平易化」は外国人や子供など語彙知識が不足している読み手の読解を補助する．これらを組み合わせ読み手に合わせてテキストを柔軟に変化させることによって電子化されたテキストを読解する幅広い層に対して読解支援を行うことが可能となる．
|
Report
(4 results)
Research Products
(5 results)
