A carregar...
Projeto de investigação
Sem título
Financiador
Autores
Publicações
Building a Corpus of Errors and Quality in Machine Translation
Publication . Costa, Ângela; Correia, Rui; Coheur, Luísa; Centro de Linguística da UNL (CLUNL)
In this paper we describe a corpus of automatic translations annotated with both error type and quality. The 300 sentences that we have selected were generated by Google Translate, Systran and two in-house Machine Translation systems that use Moses technology. The errors present on the translations were annotated with an error taxonomy that divides errors in five main linguistic categories (Orthography, Lexis, Grammar, Semantics and Discourse), reflecting the language level where the error is located. After the error annotation process, we accessed the translation quality of each sentence using a four point comprehension scale from 1 to 5. Both tasks of error and quality annotation were performed by two different annotators, achieving good levels of inter-annotator agreement. The creation of this corpus allowed us to use it as training data for a translation quality classifier. We concluded on error severity by observing the outputs of two machine learning classifiers: a decision tree and a regression model.
El-WOZ
Publication . Pellegrini, Thomas; Hedayati, Vahid; Costa, Ângela; Centro de Linguística da UNL (CLUNL)
In this paper, we present a speech recording interface developed in the context of a project on automatic speech recognition for elderly native speakers of European Portuguese. In order to collect spontaneous speech in a situation of interaction with a machine, this interface was designed as a Wizard-of-Oz (WOZ) plateform. In this setup, users interact with a fake automated dialog system controled by a human wizard. It was implemented as a client-server application and the subjects interact with a talking head. The human wizard chooses pre-defined questions or sentences in a graphical user interface, which are then synthesized and spoken aloud by the avatar on the client side. A small spontaneous speech corpus was collected in a daily center. Eight speakers between 75 and 90 years old were recorded. They appreciated the interface and felt at ease with the avatar. Manual orthographic transcriptions were created for the total of about 45 minutes of speech.
Unidades organizacionais
Descrição
Palavras-chave
Contribuidores
Financiadores
Entidade financiadora
Fundação para a Ciência e a Tecnologia
Programa de financiamento
3599-PPCDT
Número da atribuição
PEst-OE/EEI/LA0021/2013