TAILIEUCHUNG - Báo cáo khoa học: "Sentence generation as a planning problem"

We translate sentence generation from TAG grammars with semantic and pragmatic information into a planning problem by encoding the contribution of each word declaratively and explicitly. This allows us to exploit the performance of off-the-shelf planners. It also opens up new perspectives on referring expression generation and the relationship between language and action. | Sentence generation as a planning problem Alexander Koller Center for Computational Learning Systems Columbia University koller@ Matthew Stone Computer Science Rutgers University Abstract We translate sentence generation from TAG grammars with semantic and pragmatic information into a planning problem by encoding the contribution of each word declara-tively and explicitly. This allows us to exploit the performance of off-the-shelf planners. It also opens up new perspectives on referring expression generation and the relationship between language and action. 1 Introduction Systems that produce natural language must synthesize the primitives of linguistic structure into well-formed utterances that make desired contributions to discourse. This is fundamentally a planning problem Each linguistic primitive makes certain contributions while potentially introducing new goals. In this paper we make this perspective explicit by translating the sentence generation problem of TAG grammars with semantic and pragmatic information into a planning problem stated in the widely used Planning Domain Definition Language PDDL McDermott 2000 . The encoding provides a clean separation between computation and linguistic modelling and is open to future extensions. It also allows us to benefit from the past and ongoing advances in the performance of off-the-shelf planners Blum and Furst 1997 Kautz and Selman 1998 Hoffmann and Nebel 2001 . While there have been previous systems that encode generation as planning Cohen and Perrault 1979 Appelt 1985 Heeman and Hirst 1995 our approach is distinguished from these systems by its focus on the grammatically specified contributions 336 of each individual word and the TAG tree it anchors to syntax semantics and local pragmatics Hobbs et al. 1993 . For example words directly achieve content goals by adding a corresponding semantic primitive to the conversational record. We deliberately avoid reasoning about .

• Báo cáo khoa học
• Sentence generation
• planning problem
• Alexander Koller Matthew Stone
• báo cáo khoa học
• mô hình ngôn ngữ
• xử lý ngôn ngữ tự nhiên
• Sentence Ordering Driven by Local and Global
• Coherence for Summary Generation
• Renxian Zhang
• báo cáo ngôn ngữ
• ngôn ngữ tự nhiên
• Sentence Diagram Generation
• Dependency Parsing Elijah Mayfield Division
• Science and Mathematics
• Instance based Sentence Boundary
• Determination by Optimization
• Natural Language Generation
• CONTROLLED TRANSFORMATIONAL
• Madeleine Bates
• scientific reports
• model language
• process natural language
• Improving Grammaticality
• Statistical Sentence Generation Introducing a Dependency Spanning Tree Algorithm
• Argument Satisfaction Model
• Logical expression
• Discourse representation structure
• Predicate relationship
• Tree based method
• Bài giảng Xử lý ngôn ngữ tự nhiên
• Kỹ thuật lập trình
• Xử lý nhập nhằng ngữ nghĩa
• Xử lý ngữ nghĩa
• Xử lý ngôn ngữ
• Natural Language Processing
• Ngôn ngữ lập trình
• Nhập nhằng cấu trúc
• Tri thức về ngôn ngữ
• Mô hình n gram
• Dịch máy
• Phương pháp dịch máy
• Hiểu ngôn ngữ
• Phân tích ngữ nghĩa
• Phân loại tin tự động
• Biểu diễn vị từ
• Thuộc tính về sự kiện
• Thuộc tính về sự kiện
• Mô hình ngôn ngữ Google Book N grams
• Mô hình ngôn ngữ KenLM
• Phương pháp làm mịn
• Tách từ tiếng Việt
• Gán nhãn từ loại
• Phân tích cú pháp
• Nghĩa từ vựng
• Phân giải nhập nhằng từ
• Phân loại văn bản
• Lexical chain
• Phản hồi thông tin
• Bài toán PTCP
• Cấu trúc ngữ pháp
• Phân tích cú pháp xác suất
• CKY kết hợp xác suất
• Văn phạm phi ngữ cảnh xác suất
• Hình thái học