Elisabet Comelles

VERTa participation in the WMT14 Metrics Task

In this paper we present VERTa, a linguistically-motivated metric that combines linguistic features at different levels. We provide the linguistic motivation on which the metric is based, as well as describe the different modules in VERTa and how they are combined. Finally, we describe the two versions of VERTa, VERTa-EQ and VERTa-W, sent to WMT14 and report results obtained in the experiments conducted with the WMT12 and WMT13 data into English.

An information state-based dialogue manager for making voice web smarter

In this paper we propose the integration of intelligent components technologies (natural language and discourse management) in voice web interfaces to make them smarter. We describe how we have integrated reusable components of dialogue management and language processing in a multilingual voice system to improve its friendliness and portability. The dialogue management component deals with complex dialogue phenomena, such as user-initiative dialogues, and follows the information state-based theory. The resulting dialogue system supports friendly communication (through the telephone and the web) in several languages: English, Spanish, Catalan and Italian. The dialogue system has been adapted to guide the users to access online public administration services.

Guiding automatic MT evaluation by means of linguistic features

Machine translation (MT) has become increasingly important and popular in the past decade, leading to the development of MT evaluation metrics aiming at automatically assessing MT output. Most of these metrics use reference translations to compare systems output, therefore, they should not only detect MT errors but also be able to identify correct equivalent expressions so as not to penalize them when those are not displayed in the reference translations. With the aim of improving MT evaluation metrics a study has been carried out of a wide panorama of linguistic features and their implications. For that purpose a Spanish and an English corpora containing hypothesis and reference translations have been analysed from a linguistic point of view, so that common errors can be detected and positive equivalencies highlighted. This article focuses on this qualitative analysis describing the linguistic phenomena that should be considered when developing an automatic MT evaluation metric. The results of this analysis have been used to develop an automatic MT evaluation metric that takes into account different dimensions of language. A brief review of the metric and its evaluation are also provided.

VERTa: a Linguistically-motivated Metric at the WMT15 Metrics Task

This paper describes VERTa’s submission to the 2015 EMNLP Workshop on Statistical Machine Translation. VERTa is a linguistically-motivated metric that combines linguistic features at different levels. In this paper, VERTa is described briefly, as well as the three versions submitted to the workshop: VERTa70Adeq30Flu, VERTa-EQ and VERTaW. Finally, the experiments conducted with the WMT14 data are reported and some conclusions are drawn.

A Speech-to-Speech Translation System for Catalan, Spanish, and English

In this paper we describe the FAME interlingual speech-to- speech translation System for Spanish, Catalan and English which is intended to assist users in the reservation of a hotel room when calling or visiting abroad. The System has been developed as an extension of the existing NESPOLE! translation system [4] which translates between English, German, Italian and French. After a brief introduction we describe the Spanish and Catalan System components including speech recognition, transcription to IF mapping, IF to text generation and speech synthesis. We also present a task-oriented evaluation method used to inform about system development and some preliminary results.