Cross-linguistic Attribute Selection for REG: Comparing Dutch and English
نویسندگان
چکیده
In this paper we describe a cross-linguistic experiment in attribute selection for referring expression generation. We used a graph-based attribute selection algorithm that was trained and cross-evaluated on English and Dutch data. The results indicate that attribute selection can be done in a largely language independent way.
منابع مشابه
Arithmetic Aggregation Operators for Interval-valued Intuitionistic Linguistic Variables and Application to Multi-attribute Group Decision Making
The intuitionistic linguistic set (ILS) is an extension of linguisitc variable. To overcome the drawback of using single real number to represent membership degree and non-membership degree for ILS, the concept of interval-valued intuitionistic linguistic set (IVILS) is introduced through representing the membership degree and non-membership degree with intervals for ILS in this paper. The oper...
متن کاملCross Linguistic Phoneme Correspondences
Cross-linguistic phoneme correspondences, or metaphonemes1, can be defined across languages which are relatively closely related in exactly the same way as correspondences can be defined for dialects, or accents, of a single language (e.g. O’Connor, 1973; Fitt, 2001). In this paper we present the theory of metaphonemes, comparing them with traditional archiand morphophonemes as well as with sim...
متن کامل2-tuple intuitionistic fuzzy linguistic aggregation operators in multiple attribute decision making
In this paper, we investigate the multiple attribute decisionmaking (MADM) problems with 2-tuple intuitionistic fuzzylinguistic information. Then, we utilize arithmetic and geometricoperations to develop some 2-tuple intuitionistic fuzzy linguisticaggregation operators. The prominent characteristic of theseproposed operators are studied. Then, we have utilized theseoperators to develop some app...
متن کاملCrosslingual Countability Classification: English meets Dutch
This paper presents a range of methods for classifying Dutch nouns as countable, uncountable or plural only based on both Dutch and English data. The classification is based on the occurrence of countability specific linguistic features that are extracted from unannotated corpora. We show that in the absence of reliable Dutch gold standard data, cross-linguistic classification can be achieved o...
متن کاملCross-Linguistic Transfer Revisited: The Case of English and Persian
The present study sought to investigate the evidence for cross-linguistic transfer in a partial English immersion and non-immersion educational setting. To this end, a total of 145 first, third and fifth graders in a partial English immersion program and 95 students from the same grade levels in a non-immersion program were chosen. Six different English and Persian tests were administered: the ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2010