Evaluating Centering for Information Ordering Using Corpora
نویسندگان
چکیده
منابع مشابه
Evaluating Centering for Information Ordering Using Corpora
In this article we discuss several metrics of coherence defined using centering theory and investigate the usefulness of such metrics for information ordering in automatic text generation. We estimate empirically which is the most promising metric and how useful this metric is using a general methodology applied on several corpora. Our main result is that the simplest metric (which relies exclu...
متن کاملEvaluating Centering for Sentence Ordering in Two New Domains
This paper builds on recent research investigating sentence ordering in text production by evaluating the Centering-based metrics of coherence employed by Karamanis et al. (2004) using the data of Barzilay and Lapata (2005). This is the first time that Centering is evaluated empirically as a sentence ordering constraint in several domains, verifying the results reported in Karamanis et al.
متن کاملEvaluating Centering-Based Metrics of Coherence
We use a reliably annotated corpus to compare metrics of coherence based on Centering Theory with respect to their potential usefulness for text structuring in natural language generation. Previous corpus-based evaluations of the coherence of text according to Centering did not compare the coherence of the chosen text structure with that of the possible alternatives. A corpusbased methodology i...
متن کاملAligning Bilingual Corpora Using Sentences Location Information
Large amounts of bilingual resource on the Internet provide us with the probability of building a large scale of bilingual corpus. The irregular characteristics of the real texts, especially without the strictly aligned paragraph boundaries, bring a challenge to alignment technology. The traditional alignment methods have some difficulties in competency for doing this. This paper describes a ne...
متن کاملCentering Information Retrieval to the User
In this paper, we present a novel approach to text mining that helps to build intelligent user interfaces for recommender and information retrieval systems. The main problem for the user in information retrieval is that he must have almost perfect knowledge of the domain and the domain terminology. Our approach eases this burden by showing a way how to encode domain knowledge so that an informa...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Computational Linguistics
سال: 2009
ISSN: 0891-2017,1530-9312
DOI: 10.1162/coli.07-036-r2-06-22