Two Corpus Based Experiments with the Portuguese and English Wordnets
نویسندگان
چکیده
This paper presents two experiments with real world applications of word sense disambiguation, wordnets and dependency parsing. The first is an effort towards a portuguese wordnet annotated corpus. We manually annotated 30 sentences using OpenWordNet-PT as a lexicon and then compared the results with an automatic annotation. In addition to the system’s evaluation, the results provided valuable insights about how to deal with such an ambitious task. The second experiment deals with using Princeton Wordnet as part of an NLP pipeline for information extraction from technical texts in the mining domain and the issues found while integrating word sense disambiguation with a syntactic analysis of the sentences.
منابع مشابه
Bootstrapping a Portuguese WordNet from Galician, Spanish and English Wordnets
In this article we exploit the possibility on bootstrapping an European Portuguese WordNet from the English, Spanish and Galician wordnets using Probabilistic Translation Dictionaries automatically created from parallel corpora. The process generated a total of 56 770 synsets and 97 058 variants. An evaluation of the results using the Brazilian OpenWordNet-PT as a gold standard resulted on a pr...
متن کاملAutomatic creation of WordNets from parallel corpora
In this paper we present the evaluation results for the creation of WordNets for five languages (Spanish, French, German, Italian and Portuguese) using an approach based on parallel corpora. We have used three very large parallel corpora for our experiments: DGT-TM, EMEA and ECB. The English part of each corpus is semantically tagged using Freeling and UKB. After this step, the process of WordN...
متن کاملThe Presence and Influence of English in the Portuguese Financial Media
As the lingua franca of the 21st century, English has become the main language for intercultural communication for those wanting to embrace globalization. In Portugal, it is the second language of most public and private domains influencing its culture and discourses. Language contact situations transform languages by the incorporations they make from other languages and Portugal has...
متن کاملHedges in English for Academic Purposes: A Corpus-based study of Iranian EFL learners
Hedges, as tools to express tentativeness and doubt, have been studied in plenty of research papers in the Iranian EFL research setting. However, their use in a learner corpus, portraying Iranian learner English, is in need of more research attention. With this end in view, this study aimed at investigating how Iranian EFL learners who have majored in English-related fields in Iran deployed hed...
متن کاملGMM-Based Identification of Indonesian Speech
This paper reports the performance of identification of Indonesian speech within a ten-language corpus: English, German, Hungarian, Indonesian, Italian, Korean, Mandarin, Polish, Portuguese, and Swedish. The tasks are performed by implementing Gaussian Mixture Model (GMM) on MelFrequency Cepstral Coefficients (MFCCs). Two types of experiments that have been undertaken: pair-wise and tenlanguage...
متن کامل