TAILIEUCHUNG - Báo cáo khoa học: "Generating Referring Expressions in Open Domains"

We present an algorithm for generating referring expressions in open domains. Existing algorithms work at the semantic level and assume the availability of a classification for attributes, which is only feasible for restricted domains. Our alternative works at the realisation level, relies on WordNet synonym and antonym sets, and gives equivalent results on the examples cited in the literature and improved results for examples that prior approaches cannot handle. | Generating Referring Expressions in Open Domains Advaith Siddharthan Computer Science Department Columbia University as372@ Ann Copestake Computer Laboratory University of Cambridge aac10@ Abstract We present an algorithm for generating referring expressions in open domains. Existing algorithms work at the semantic level and assume the availability of a classification for attributes which is only feasible for restricted domains. Our alternative works at the realisation level relies on Word-Net synonym and antonym sets and gives equivalent results on the examples cited in the literature and improved results for examples that prior approaches cannot handle. We believe that ours is also the first algorithm that allows for the incremental incorporation of relations. We present a novel corpus-evaluation using referring expressions from the Penn Wall Street Journal Treebank. 1 Introduction Referring expression generation has historically been treated as a part of the wider issue of generating text from an underlying semantic representation. The task has therefore traditionally been approached at the semantic level. Entities in the real world are logically represented for example ignoring quantifiers a big brown dog might be represented as bigl x A brownl x A dogl x where the predicates bigl brownl and dogl represent different attributes of the variable entity x. The task of referring expression generation has traditionally been framed as the identification of the shortest logical description for the referent entity that differentiates it from all other entities in the discourse domain. For example if there were a small brown dog smalll x A brownl x A dogl x in context the minimal description for the big brown dog would be bigl x A dogl x 1. This semantic framework makes it difficult to apply existing referring expression generation algorithms to the many regeneration tasks that are important today for example summarisation open-ended question .

• Báo cáo khoa học
• Generating Referring Expressions
• Open Domains
• Advaith Siddharthan Ann Copestake
• báo cáo khoa học
• mô hình ngôn ngữ
• xử lý ngôn ngữ tự nhiên
• Using aggregation
• selecting content
• A Best First Search Algorithm
• Helmut Horacek
• scientific reports
• model language
• process natural language
• a unification grammar
• Richard Power
• Involving Relations
• Long Papers
• Bài giảng Xử lý ngôn ngữ tự nhiên
• 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