• Aucun résultat trouvé

Spanish FrameNet. An on-line lexical resource and its application to NLP

N/A
N/A
Info
Télécharger
Protected

Academic year: 2022

Partager "Spanish FrameNet. An on-line lexical resource and its application to NLP"

Copied!
1
0
0

Chargement.... (Voir le texte intégral maintenant)

Texte intégral

(1)

Spanish Frameet. An on-line lexical resource and its application to LP

Carlos Subirats

Universitat Autonoma de Barcelona - Spain and Berkeley- USA

Spanish FrameNet (SFN *) is a research project which is developed at the Autonomous University of Barcelona (Spain) and the International Computer Science Institute (Berkeley, CA) in cooperation with the FrameNet Project.

SFN is creating an online lexical resource for Spanish, based on frame semantics (Fillmore 1982, 1985) and supported by corpus evidence. The basic aim of the project is to develop a semantically and syntactically annotated lexical resource with broad lexical coverage in Spanish which can be used as a training corpus for applications aimed at automatic semantic role labeling (Erk and Padó 2006). In its present state, SFN contains more than 1,000 lexical items, basically, verbs, nouns, and adjectives, representative of a wide range of semantic domains. The aim is to document the range of semantic and syntactic combinatory possibilities (valences) of each word in each of its senses through semiautomatic annotated example sentences and automatic capture and organization of the annotation results. The results of this project can be browsed on the web (http://gemini.uab.es/SFN) using several web report generators which support a variety of queries about the general description of the semantic frames and their frame elements. The semantically and syntactically annotated corpus sentences display the syntactic realizations of frame elements as well as their respective phrase types and grammatical functions.

* SFN is sponsored by the Department of Science and Innovationof Spain (FFI2008-0875) and the Fundación Comillas .

Références

Télécharger maintenant ( PDF - 1 Page - 65.14 KB )

Documents relatifs

A Lexical-Semantic Approach to AVE

In our case, we establish the following constraint: “In order to be considered as a candidate entailment pair, the hypothesis’ entities must also appear within the supporting text

Experiments for Tuning the Values of Lexical Features in Question Answering for Spanish

Factoid questions resolution relies on a hybrid system involving the following stages: question processing, which includes the extraction of named entities and lexical context in

The Use of Lexical Context in Question Answering for Spanish

This fact, along with the inclusion of QA evaluation as part of the Text Retrieval Conference (TREC) 1 in 1999, and recently [6] in Multilingual Question Answering as part of

Lexical Normalization of Spanish Tweets with Rule-Based Components and Language Models

Abstract: This paper presents a system to normalize Spanish tweets, which uses preprocessing rules, a domain-appropriate edit-distance model, and language models to select

FLELex: a graded lexical resource for French foreign learners

In this paper we present FLELex, the first graded lexicon for French as a foreign language (FFL) that reports word frequencies by difficulty level (according to the CEFR scale).. It

Lexical and Non-lexical Tone and Prosodic Typology

In this presentation I have tried to show that while the prosodic characteristics of languages may appear very different when considered from the point of view of lexical

Inferences for Lexical Semantic Resource Building with Less Supervision

According to those observations, we hypothesise that the semantic relations extracted from corpora in a syntactic fea- ture rich language such as Russian can be used to enrich

Towards Lexical Encoding of Multiword Expressions in Spanish Dialects [WG1]

Extract of the encoding of a sample MWE hablar paja (lit. ’to talk straw’) with 3 different meanings according to the dialect..