Pasar al contenido principal

Resultados relacionados

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

RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Towards Using Web-Crawled Data for Domain Adaptation in Statistical Machine Translation

  • Pecina, Pavel
  • Toral, Antonio
  • Way, Andy
  • Papavassiliou, Vassilis
  • Prokopidis, Prokopis
  • Giagkou, Maria
  • Toral, Antonio|||/items/ffa766b5-dbe2-4105-a0fc-e51f29946693
This paper reports on the ongoing work focused on domain adaptation of statistical machine translation using domain-specific data obtained by domain-focused web crawling. We present a strategy for crawling monolingual and parallel data and their exploitation for testing, language modelling, and system tuning in a phrase-based machine translation framework. The proposed approach is evaluated on the domains of Natural Environment and Labour Legislation and two language pairs: English–French and English–Greek.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Simple and Effective Parameter Tuning for Domain Adaptation of Statistical Machine Translation

  • Pecina, Pavel
  • Toral, Antonio
  • van Genabith, Josef
  • Toral, Antonio|||/items/ffa766b5-dbe2-4105-a0fc-e51f29946693
Current state-of-the-art Statistical Machine Translation systems are based on log-linear models that combine a set of feature functions to score translation hypotheses during decoding. The models are parametrized by a vector of weights usually optimized on a set of sentences and their reference translations, called development data. In this paper, we explore a (common and industry relevant) scenario where a system trained and tuned on general domain data needs to be adapted to a specific domain for which no or only very limited in-domain bilingual data is available. It turns out that such systems can be adapted successfully by re-tuning model parameters using surprisingly small amounts of parallel in-domain data, by cross-tuning or no tuning at all. We show in detail how and why this is effective, compare the approaches and effort involved. We also study the effect of system hyperparameters (such as maximum phrase length and development data size) and their optimal values in this scenario.
Recercat. Dipósit de la Recerca de Catalunya
Publicación Otros (Other)

PANACEA: PAROLE Association Workshop 18/19 Octobre 2012

Recercat. Dipósit de la Recerca de Catalunya
Publicación Otros (Other)

PANACEA: LREC 2012, EC Projects Session