1 |
Análise sintática automática de texto real com estruturas desviantes: o desempenho de sistemas de parsing baseados em dependências com textos de aprendentes de Português L2/LE
|
|
|
|
BASE
|
|
Show details
|
|
2 |
Reflexão sobre opções linguísticas em Tradução: traduções jurídicas oficiais inglês-português e português-inglês
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Relatório de estágio no Camões, I.P. : análise de fenómenos lexicais na tradução de textos técnicos
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Relatório de estágio curricular no Camões, I.P. : léxico e tradução
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Quality in human post-editing of machine-translated texts : error annotation and linguistic specifications for tackling register errors
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Using unmarked contexts in nominal lexical semantic classification
|
|
|
|
BASE
|
|
Show details
|
|
7 |
LexTec - a rich language resource for technical domains in Portuguese
|
|
|
|
BASE
|
|
Show details
|
|
9 |
Relatório de estágio no Camões, I.P. : discussão sobre opções linguísticas relevantes para a tradução
|
|
|
|
BASE
|
|
Show details
|
|
10 |
Quality in machine translation and human post-editing : error annotation and specifications
|
|
|
|
BASE
|
|
Show details
|
|
11 |
Using qualia information to identify lexical semantic classes in an unsupervised clustering task ...
|
|
|
|
BASE
|
|
Show details
|
|
12 |
Syntax and semantics of adjectives in portuguese analysis and modeling
|
|
|
|
BASE
|
|
Show details
|
|
13 |
Towards the automatic classification of complex-type nominals
|
|
|
|
BASE
|
|
Show details
|
|
15 |
Using qualia information to identify lexical semantic classes in an unsupervised clustering task
|
|
|
|
BASE
|
|
Show details
|
|
16 |
Using unmarked contexts in nominal lexical semantic classification
|
|
|
|
BASE
|
|
Show details
|
|
17 |
Reading between the lines: overcoming data sparsity for accurate classification of lexical relationships
|
|
|
|
Abstract:
Comunicació presentada a: 4th Joint Conference on Lexical and Computational Semantics, celebrada a Denver, Colorado, Estats Units d'Amèrica, del 4 al 5 de juny de 2015. ; The lexical semantic relationships between word pairs are key features for many NLP tasks. Most approaches for automatically classifying related word pairs are hindered by data sparsity because of their need to observe two words co-occurring in order to detect the lexical relation holding between them. Even when mining very large corpora, not every related word pair co-occurs. Using novel representations based on graphs and word embeddings, we present two systems that are able to predict relations between words, even when these are never found in the same sentence in a given corpus. In two experiments, we demonstrate superior performance of both approaches over the state of the art, achieving significant gains in recall. ; The authors gratefully acknowledge the support of the CLARA project (EU-7FP-ITN-238405), the SKATER project (Ministerio de Economia y Competitividad, TIN2012-38584-C06-05) and of the MultiJEDI ERC Starting Grant no. 259234.
|
|
URL: http://hdl.handle.net/10230/36672
|
|
BASE
|
|
Hide details
|
|
|
|