Corpus-Based Acquisition of Support Verb
Constructions for Portuguese
B. Zeller, and S. Padó. Proceedings of PROPOR 2012, page 73--84. Coimbra, Portugal, (2012)
Abstract
We present a resource-poor approach to automatically acquire support verb constructions (SVCs) for Portuguese with a two-stage procedure. First, we apply a cross-lingual approach with a bilingual par- allel corpus: starting with a Portuguese full verb, we use the translations into another language and the corresponding backtranslations to identify Portuguese verb-noun pairs with the same meaning. Since not all of these are SVCs, the candidates are ranked and filtered in a second, monolingual step based on association statistics. We discuss two parametrisations of our procedure for a high-precision and a high-recall setting. In our experiments, these parametrizations achieve a maximum precision of 91\% and a maximum recall of 86\%, respectively.
%0 Conference Paper
%1 zeller12:_corpus_based_acquis_of_suppor
%A Zeller, Britta
%A Padó, Sebastian
%B Proceedings of PROPOR 2012
%C Coimbra, Portugal
%D 2012
%K conference myown
%P 73--84
%T Corpus-Based Acquisition of Support Verb
Constructions for Portuguese
%U https://doi.org/10.1007/978-3-642-28885-2_8
%X We present a resource-poor approach to automatically acquire support verb constructions (SVCs) for Portuguese with a two-stage procedure. First, we apply a cross-lingual approach with a bilingual par- allel corpus: starting with a Portuguese full verb, we use the translations into another language and the corresponding backtranslations to identify Portuguese verb-noun pairs with the same meaning. Since not all of these are SVCs, the candidates are ranked and filtered in a second, monolingual step based on association statistics. We discuss two parametrisations of our procedure for a high-precision and a high-recall setting. In our experiments, these parametrizations achieve a maximum precision of 91\% and a maximum recall of 86\%, respectively.
@inproceedings{zeller12:_corpus_based_acquis_of_suppor,
abstract = {We present a resource-poor approach to automatically acquire support verb constructions (SVCs) for Portuguese with a two-stage procedure. First, we apply a cross-lingual approach with a bilingual par- allel corpus: starting with a Portuguese full verb, we use the translations into another language and the corresponding backtranslations to identify Portuguese verb-noun pairs with the same meaning. Since not all of these are SVCs, the candidates are ranked and filtered in a second, monolingual step based on association statistics. We discuss two parametrisations of our procedure for a high-precision and a high-recall setting. In our experiments, these parametrizations achieve a maximum precision of 91\% and a maximum recall of 86\%, respectively.},
added-at = {2017-04-03T19:28:28.000+0200},
address = {Coimbra, Portugal},
author = {Zeller, Britta and Pad{\'o}, Sebastian},
biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2d2509634c71a6e9361bc15dc40ba5b4a/sp},
booktitle = {Proceedings of PROPOR 2012},
interhash = {3630d8f660d56ba27e71ddcf383f6f78},
intrahash = {d2509634c71a6e9361bc15dc40ba5b4a},
keywords = {conference myown},
pages = {73--84},
timestamp = {2019-07-06T20:07:27.000+0200},
title = {Corpus-Based Acquisition of Support Verb
Constructions for {P}ortuguese},
url = {https://doi.org/10.1007/978-3-642-28885-2_8},
year = 2012
}