Bridging Textual Ellipses

نویسندگان

  • Udo Hahn
  • Michael Strube
  • Katja Markert
چکیده

We present a hybrid text understanding methodology for the resolution of textual ellipsis. It integrates language-independent conceptual criteria and language-dependent functional constraints. The methodological framework for text ellipsis resolution is the centering model that has been adapted to constraints reflecting the functional information structure within utterances, i.e., the distinction between context-bound and unbound discourse elements.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

A SEMANTIC COPYING MODEL FORUNDERSTANDING COMPARATIVESSte

We propose a model of computational semantic interpretation of comparatives which is based on a mechanism for semantic copying. While the treatment of phrasal and clausal forms of comparatives we give is in line with previous approaches to their semantic description, our model also incorporates the analysis of textual phenomena that interact with the interpretation of comparatives, viz. metonym...

متن کامل

Annotating Extended Textual Coreference and Bridging Relations in the Prague Dependency Treebank

This technical report describes the project of manual annotation of extended textual coreference and bridging relations, which runs at the Institute of Formal and Applied Linguistics, Faculty of Mathematics and Physics, Charles University in Prague, since 2009. It contains the typology of coreference and bridging relations, classification of elements that are annotated for coreference and the a...

متن کامل

Inferring semantics from textual information in multimedia retrieval

We propose a method for inferring semantic information from textual data in content-based multimedia retrieval. Training examples of images and videos belonging to a specific semantic class are associated with their low-level visual and aural descriptors augmented with textual features such as frequencies of significant words. A fuzzy mapping of a semantic class in the training set to a class o...

متن کامل

Text structures in medical text processing: empirical evidence and a text understanding prototype

We consider the role of textual structures in medical texts. In particular, we examine the impact the lacking recognition of text phenomena has on the validity of medical knowledge bases fed by a natural language understanding front-end. First, we review the results from an empirical study on a sample of medical texts considering, in various forms of local coherence phenomena (anaphora and text...

متن کامل

How Dependency Trees and Tectogrammatics Help Annotating Coreference and Bridging Relations in Prague Dependency Treebank

In this paper, we explore the benefits of dependency trees and tectogrammatical structure used in the Prague Dependency Treebank for annotating language phenomena that cross the sentence boundary, namely coreference and bridging relations. We present the benefits of dependency trees such as the detailed processing of ellipses, syntactic decisions for coordination and apposition structures that ...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 1996