TAILIEUCHUNG - Báo cáo khoa học: "Disambiguating Between Generic and Referential “You” in Dialog ∗"

We describe an algorithm for a novel task: disambiguating the pronoun you in conversation. You can be generic or referential; finding referential you is important for tasks such as addressee identification or extracting ‘owners’ of action items. Our classifier achieves 84% accuracy in two-person conversations; an initial study shows promising performance even on more complex multi-party meetings. | Disambiguating Between Generic and Referential You in Dialog Surabhi Gupta Matthew Purver Department of Computer Science Center for the Study Stanford University of Language and Information Stanford CA 94305 US Stanford University surabhi@ Stanford CA 94305 US mpurver@ Dan Jurafsky Department of Linguistics Stanford University Stanford CA 94305 US jurafsky@ Abstract We describe an algorithm for a novel task disambiguating the pronoun you in conversation. You can be generic or referential finding referential you is important for tasks such as addressee identification or extracting owners of action items. Our classifier achieves 84 accuracy in two-person conversations an initial study shows promising performance even on more complex multi-party meetings. 1 Introduction and Background This paper describes an algorithm for disambiguating the generic and referential senses of the pronoun you. Our overall aim is the extraction of action items from multi-party human-human conversations concrete decisions in which one or more individuals take on a group commitment to perform a given task Purver et al. 2006 . Besides identifying the task itself it is crucial to determine the owner or person responsible. Occasionally the name of the responsible party is mentioned explicitly. More usually the owner is addressed directly and therefore referred to using a second-person pronoun as in example 1 .1 tecting the fact that a task is being assigned and in identifying the owner. While there is an increasing body of work concerning addressee identification Katzenmaier et al. 2004 Jovanovic et al. 2006 there is very little investigating the problem of second-person pronoun resolution and it is this that we address here. Most cases of you do not in fact refer to the addressee but are generic as in example 3 automatic referentiality classi cation is therefore very important. 3 B Well usually what you do is just wait until you think it s stopped and .

• Báo cáo khoa học
• Disambiguating
• Generic and Referential
• Surabhi Gupta Matthew Purver Dan Jurafsky
• báo cáo khoa học
• mô hình ngôn ngữ
• xử lý ngôn ngữ tự nhiên
• Disambiguating Temporal–Contrastive Discourse Connectives
• Long Papers
• Machine Translation
• báo cáo ngôn ngữ
• ngôn ngữ tự nhiên
• The Role of Semantic Roles
• Disambiguating Verb Senses
• Hoa Trang Dang
• Disambiguating Grammatically
• Ambiguous Sentences By Asking
• scientific reports
• model language
• process natural language
• INTERPRETING VERB EFINITIONS
• Yael Ravin
• 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