JAIST Repository >
School of Information Science >
Grants-in-aid for Scientific Research Papers >
FY 2011 >

Please use this identifier to cite or link to this item: http://hdl.handle.net/10119/10588

Title: 文から論理表現への文脈依存変換を学習するための半教師モデル
Other Titles: Contextual information and semi-supervised models for transforming sentence to logical form representation
Authors: グエン, ミン レ
Authors(alternative): Nguyen, Minh Le
Keywords: 意味解析
Issue Date: 4-Jun-2012
Abstract: 意味解析の改良をねらい,文脈素性を用いる方法を実装することを主に研究した.また,意味解析モデルを実装するのにラベルなしデータがどのように有効かについても研究しました. これらの点に関して,注釈のない大規模コーパスを語クラスタモデルによりモデル化し,識別学習モデルのための素性を抽出しました. 意味表現と自然言語文の同期モデルを学習するために,forest-to-string 法を適用した. この問題に対し,我々は,機械学習および線型計画法を用いて,法令条文の項(paragraph)の論理構造を2 段階で学習する新しい枠組みし示した. : The main goal of our research is to implement the method of using contextual features for improving semantic parsing problems. We also study how unlabeled data could help to implement semantic parsing model further. As a result, we exploited word-cluster models to model a large un-annotated corpus, to extract features for discriminative learning models. In addition, we also introduce a novel semi supervised learning model for semantic parsing with ambiguous supervision. We applied the forest-to-string method for learning the synchronous model between semantic representation and natural language sentence. We also present a novel two-phase framework to learn logical structures of paragraphs in legal articles using machine learning and integer linear programming.
Description: 研究種目:若手研究(B)
Language: jpn
URI: http://hdl.handle.net/10119/10588
Appears in Collections:2011年度 (FY 2011)

Files in This Item:

File Description SizeFormat
22700139seika.pdf133KbAdobe PDFView/Open

All items in DSpace are protected by copyright, with all rights reserved.


Contact : Library Information Section, Japan Advanced Institute of Science and Technology