TAILIEUCHUNG - Báo cáo khoa học: "The aim of such application is to attribute a title for a given text"

This paper deals with an application of automatic titling. The aim of such application is to attribute a title for a given text. So, our application relies on three very different automatic titling methods. The first one extracts relevant noun phrases for their use as a heading, the second one automatically constructs headings by selecting words appearing in the text, and, finally, the third one uses nominalization in order to propose informative and catchy titles. Experiments based on 1048 titles have shown that our methods provide relevant titles. . | Just Title It by an Online Application Cedric Lopez Violaine Prince and Mathieu Roche LIRMM CNRS University of Montpellier 2 161 rue Ada Montpellier France lopez prince mroche @ Abstract This paper deals with an application of automatic titling. The aim of such application is to attribute a title for a given text. So our application relies on three very different automatic titling methods. The first one extracts relevant noun phrases for their use as a heading the second one automatically constructs headings by selecting words appearing in the text and finally the third one uses nominalization in order to propose informative and catchy titles. Experiments based on 1048 titles have shown that our methods provide relevant titles. 1 Introduction The important amount of textual documents is in perpetual growth and requires robust applications. Automatic titling is an essential task for several applications Automatic titling of e-mails without subjects text generation summarization and so forth. Furthermore a system able to title HTML documents and so to respect one of the W3C standards about Web site accessibility is quite useful. The titling process goal is to provide a relevant representation of a document content. It might use metaphors humor or emphasis thus separating a titling task from a summarization process proving the importance of the rhetorical status in both tasks. This paper presents an original application consisting in titling all kinds of texts. For that purpose our application offers three main methods. The first one called POSTIT extracts noun phrases to be used as headings the second one called CATIT automatically builds titles by selecting words appearing in the text and finally the third one called NOMIT uses nominalization in order to propose relevant titles. Morphologic and semantic treatments are applied to obtain titles close to real titles. In particular titles have to respect two characteristics Relevance and catchiness. 2 Text .

TỪ KHÓA LIÊN QUAN
Đã phát hiện trình chặn quảng cáo AdBlock
Trang web này phụ thuộc vào doanh thu từ số lần hiển thị quảng cáo để tồn tại. Vui lòng tắt trình chặn quảng cáo của bạn hoặc tạm dừng tính năng chặn quảng cáo cho trang web này.