Guessing Hierarchies and Symbols for Word Meanings through Hyperonyms and Conceptual Vectors

نویسنده

  • Mathieu Lafourcade
چکیده

The NLP team of LIRMM currently works on lexical disambiguation and thematic text analysis [Lafourcade, 2001]. We built a system, with automated learning capabilities, based on conceptual vectors for meaning representation. Vectors are supposed to encode ideas associated to words or expressions. In the framework of knowledge and lexical meaning representation, we devise some conceptual vectors based strategies to automatically construct hierarchical taxonomies and validate (or invalidate) hyperonymy (or superordinate) relations among terms. Conceptual vectors are used through the thematic distance for decision making and link quality assessment.

برای دانلود رایگان 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

Construction of an Objective Hierarchy of Abstract Concepts via Directional Similarity

The method of organization of word meanings is a crucial issue with lexical databases. Our purpose in this research is to extract word hierarchies from corpora automatically. Our initial task to this end is to determine adjective hyperonyms. In order to find adjective hyperonyms, we utilize abstract nouns. We constructed linguistic data by extracting semantic relations between abstract nouns an...

متن کامل

Synthesizing a large concept hierarchy from French hyperonyms

The KAI,II'SOS prototype we have developed at the IBM Paris Scientific Center is able to analyze texts written in l;reneh and to produce a semantic representalion of these texts expressed as a set of inter-related Conceptual Graphs [6, 1]. It uses a semantic lexicon which contains, for each word to be defined, one or more Conceptual Graphs corresponding to one or more meanings of the word. The ...

متن کامل

Artificial Ants for Natural Language Processing

The global sense of a text results from the interactions between the different meanings of the words that compose it. Classical approaches for applications like Word Sense Disambiguation (WSD) rely on the use of conceptual vectors that represent word meanings by concept activations. The process for determining the global sense of a text consists in propagating the different vectors within the t...

متن کامل

The Effect of Conceptual Metaphor Awareness on Learning Phrasal Verbs by Iranian Intermediate EFL Learners

The ability to comprehend and produce phrasal verbs, as lexical chunks or groups of words which are commonly found together, is an important part of language learning. This study investigates the effect of ‘conceptual metaphor awareness’, as a newly developed technique in Cognitive Linguistics, on learning phrasal verbs by Iranian intermediate EFL learners. To meet this objective, two intact ho...

متن کامل

Low Cost Automated Conceptual Vector Generation from Mono and Bilingual Ressources

This paper assess the possibilities of constructing a multilingual lexicon by propagating conceptual vectors through several monolingual and bilingual resources. The system is based on a vector model in order to learn meanings to potentially select and classify meanings. Bilingual resources ensure the possibility to project vectors on the target lexicon and semantic space.

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

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2002