Building a Cross-lingual Referential Knowledge Database using Dictionaries

نویسندگان

  • Shigeko Nariyama
  • Takaaki Tanaka
  • Eric Nichols
  • Francis Bond
  • Hiromi Nakaiwa
چکیده

Referential knowledge is vital for resolving various problems in NLP, such as anaphora resolution. For example, we have the referential knowledge that diagnose is most likely a member of the referential relation ‘doctor diagnose patient’s illness’. Nariyama et al. (2005) presented an inventory of such referents as doctor, collected from Japanese dictionary definition sentences. Such referential information is based on world knowledge and is applicable across languages. This paper describes our work using the inventory to build a crosslingual referential database for multilingual applications.

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

Generating Cross-lingual Concept Space from Parallel Corpora on the Web

The information available in languages other than English on the World Wide Web is increasing significantly. To cross language boundaries between different languages, dictionaries are the most typical tools. However, the general-purpose dictionary is less sensitive in genre and domain and it is impractical to manually construct tailored bilingual dictionaries or sophisticated multilingual thesa...

متن کامل

From free shallow monolingual resources to machine translation systems: easing the task

The availability of machine-readable bilingual linguistic resources is crucial not only for machine translation but also for other applications such as cross-lingual information retrieval. However, the building of such resources demands extensive manual work. This paper describes a methodology to build automatically bilingual dictionaries and transfer rules by extracting knowledge from word-ali...

متن کامل

From free shallow monolingual resources to machine translation systems

The availability of machine-readable bilingual linguistic resources is crucial not only for machine translation but also for other applications such as cross-lingual information retrieval. However, the building of such resources demands extensive manual work. This paper describes a methodology to build automatically bilingual dictionaries and transfer rules by extracting knowledge from word-ali...

متن کامل

Bilingual emb e ddings with random walks over multilingual wordnets

Bilingual word embeddings represent words of two languages in the same space, and allow to transfer knowledge from one language to the other without machine translation. The main approach is to train monolingual embeddings first and then map them using bilingual dictionaries. In this work, we present a novel method to learn bilingual embeddings based on multilingual knowledge bases (KB) such as...

متن کامل

A Machine Learning Approach to Building Aligned Wordnets

WordNet is a lexical database describing English words and their senses. We propose a method for automatically producing similar resources for new languages by taking advantage of the original WordNet in conjunction with translation dictionaries. A small set of training mappings is used to learn a model for predicting associations between terms and senses. The associations are represented using...

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 2005