Skip to main content

Resultados relacionados

Resultados totales (Incluyendo duplicados): 4
Encontrada(s) 1 página(s)

Repositorio Digital de la UPF
Publication Artículo científico (JournalArticle)

Robust multilingual Named Entity Recognition with shallow semi-supervised features

  • Agerri, Rodrigo
  • Rigau Claramunt, German
We present a multilingual Named Entity Recognition approach based on a robust and general set of features across languages and datasets. Our system combines shallow local information with clustering semi-supervised features induced on large amounts of unlabeled text. Understanding via empirical experimentation how to effectively combine various types of clustering features allows us to seamlessly export our system to other datasets and languages. The result is a simple but highly competitive system which obtains state of the art results across five languages and twelve datasets. The results are reported on standard shared task evaluation data such as CoNLL for English, Spanish and Dutch. Furthermore, and despite the lack of linguistically motivated features, we also report best results for languages such as Basque and German. In addition, we demonstrate that our method also obtains very competitive results even when the amount of supervised data is cut by half, alleviating the dependency on manually annotated data. Finally, the results show that our emphasis on clustering features is crucial to develop robust out-of-domain models. The system and models are freely available to facilitate its use and guarantee the reproducibility of results., This work has been supported by the European projects NewsReader, EC/FP7/316404 and QTLeap – EC/FP7/610516, and by the Spanish Ministry of Economy and Competitiveness (MINECO) SKATER, Grant No. TIN2012-38584-C06-01 and TUNER, TIN2015-65308-C5-1-R.
RUA. Repositorio Institucional de la Universidad de Alicante
Publication Otros (Other)

Tectogrammar-based machine translation for English-Spanish and English-Basque, Traducción automática basada en tectogramática para inglés-español e inglés-euskara

  • Aranberri, Nora
  • Labaka Intxauspe, Gorka
  • Jauregi, Oneka
  • Díaz de Ilarraza Sánchez, Arantza
  • Alegría Loinaz, Iñaki
  • Agirre Bengoa, Eneko
Presentamos los primeros sistemas de traducción automática para inglés-español e inglés-euskara basados en tectogramática. A partir del modelo ya existente inglés-checo, describimos las herramientas para el análisis y síntesis, y los recursos para la trasferencia. La evaluación muestra el potencial de estos sistemas para adaptarse a nuevas lenguas y dominios.
RUA. Repositorio Institucional de la Universidad de Alicante
Publication Otros (Other)

Lexical semantics, Basque and Spanish in QTLeap: Quality Translation by Deep Language Engineering Approaches, QTLeap - Traducción de calidad mediante tratamientos profundos de ingeniería lingüística

  • Agirre Bengoa, Eneko
  • Alegría Loinaz, Iñaki
  • Aranberri, Nora
  • Artetxe, Mikel
  • Barrena, Ander
  • Branco, António
  • Díaz de Ilarraza Sánchez, Arantza
  • Gojenola Galletebeitia, Koldo
  • Labaka Intxauspe, Gorka
  • Otegi, Arantxa
  • Sarasola Gabiola, Kepa
The goal of this FP7 European project is to contribute for the advancement of quality machine translation by pursuing an approach that further relies on semantics, deep parsing and linked open data.
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

Robust multilingual Named Entity Recognition with shallow semi-supervised features

  • Agerri, Rodrigo
  • Rigau Claramunt, German
We present a multilingual Named Entity Recognition approach based on a robust and general set of features across languages and datasets. Our system combines shallow local information with clustering semi-supervised features induced on large amounts of unlabeled text. Understanding via empirical experimentation how to effectively combine various types of clustering features allows us to seamlessly export our system to other datasets and languages. The result is a simple but highly competitive system which obtains state of the art results across five languages and twelve datasets. The results are reported on standard shared task evaluation data such as CoNLL for English, Spanish and Dutch. Furthermore, and despite the lack of linguistically motivated features, we also report best results for languages such as Basque and German. In addition, we demonstrate that our method also obtains very competitive results even when the amount of supervised data is cut by half, alleviating the dependency on manually annotated data. Finally, the results show that our emphasis on clustering features is crucial to develop robust out-of-domain models. The system and models are freely available to facilitate its use and guarantee the reproducibility of results., This work has been supported by the European projects NewsReader, EC/FP7/316404 and QTLeap – EC/FP7/610516, and by the Spanish Ministry of Economy and Competitiveness (MINECO) SKATER, Grant No. TIN2012-38584-C06-01 and TUNER, TIN2015-65308-C5-1-R.