Mireia Farrús

Study and correlation analysis of linguistic, perceptual, and automatic machine translation evaluations

Evaluation of machine translation output is an important task. Various human evaluation techniques as well as automatic metrics have been proposed and investigated in the last decade. However, very few evaluation methods take the linguistic aspect into account. In this article, we use an objective evaluation method for machine translation output that classifies all translation errors into one of the five following linguistic levels: orthographic, morphological, lexical, semantic, and syntactic. Linguistic guidelines for the target language are required, and human evaluators use them in to classify the output errors. The experiments are performed on Englishto-Catalan and Spanish-to-Catalan translation outputs generated by four different systems: 2 rule-based and 2 statistical. All translations are evaluated using the 3 following methods: a standard human perceptual evaluation method, several widely used automatic metrics, and the human linguistic evaluation. Pearson and Spearman correlation coefficients between the linguistic, perceptual, and automatic results are then calculated, showing that the semantic level correlates significantly with both perceptual evaluation and automatic metrics.

Audio, video and multimodal person identification in a smart room

In this paper, we address the modality integration issue on the example of a smart room environment aiming at enabling person identification by combining acoustic features and 2D face images. First we introduce the monomodal audio and video identification techniques and then we present the use of combined input speech and face images for person identification. The various sensory modalities, speech and faces, are processed both individually and jointly. Its shown that the multimodal approach results in improved performance in the identification of the participants.

Statistical machine translation enhancements through linguistic levels: A survey

Machine translation can be considered a highly interdisciplinary and multidisciplinary field because it is approached from the point of view of human translators, engineers, computer scientists, mathematicians, and linguists. One of the most popular approaches is the Statistical Machine Translation (smt) approach, which tries to cover translation in a holistic manner by learning from parallel corpus aligned at the sentence level. However, with this basic approach, there are some issues at each written linguistic level (i.e., orthographic, morphological, lexical, syntactic and semantic) that remain unsolved. Research in smt has continuously been focused on solving the different linguistic levels challenges. This article represents a survey of how the smt has been enhanced to perform translation correctly at all linguistic levels.

Histogram equalization in SVM multimodal person verification

It has been shown that prosody helps to improve voice spectrum based speaker recognition systems. Therefore, prosodic features can also be used in multimodal person verification in order to achieve better results. In this paper, a multimodal recognition system based on facial and vocal tract spectral features is improved by adding prosodic information. Matcher weighting method and support vector machines have been used as fusion techniques, and histogram equalization has been applied before SVM fusion as a normalization technique. The results show that the performance of a SVM multimodal verification system can be improved by using histogram equalization, especially when the equalization is applied to those scores giving the highest EER values.

Towards human linguistic machine translation evaluation

When evaluating machine translation outputs, linguistics is usually taken into account implicitly. Annotators have to decide whether a sentence is better than another or not, using, for example, adequacy and fluency criteria or, as recently proposed, editing the translation output so that it has the same meaning as a reference translation, and it is understandable . Therefore, the important fields of linguistics of meaning (semantics) and grammar (syntax) are indirectly considered. In this study, we propose to go one step further towards a linguistic human evaluation. The idea is to introduce linguistics implicitly by formulating precise guidelines. These guidelines strictly mark the difference between the sub-fields of linguistics such as: morphology, syntax, semantics, and orthography. We show our guidelines have a high inter-annotation agreement and wide-error coverage. Additionally, we examine how the linguistic human evaluation data correlate with: among different types of machine translation systems (rule and statistical-based); and with adequacy and fluency.

KRISTINA: A Knowledge-Based Virtual Conversation Agent

We present an intelligent embodied conversation agent with linguistic, social and emotional competence. Unlike the vast majority of the state-of-the-art conversation agents, the proposed agent is constructed around an ontology-based knowledge model that allows for flexible reasoning-driven dialogue planning, instead of using predefined dialogue scripts. It is further complemented by multimodal communication analysis and generation modules and a search engine for the retrieval of multimedia background content from the web needed for conducting a conversation on a given topic. The evaluation of the 1st prototype of the agent shows a high degree of acceptance of the agent by the users with respect to its trustworthiness, naturalness, etc. The individual technologies are being further improved in the 2nd prototype.

New ethical challenges for today engineering and technology

New ethical challenges related to feminine values have emerged this century.These demanding ethical values justify the involvement of women in technical fields.Engineering and technical careers will benefit from the added diversity. This paper is about the intersection of three related areas: ethics, gender and the field of engineering. It is important to focus on the attitudes and values woven through this intersection because they become essential for the complete development of the moral life of the engineering profession and of the awareness of the fact that this is a profession made up of both male and female professionals. Thus, specific behaviour coming from the feminine part is necessary in order to contribute to enriching the features of the engineering profile. An approach particularly attached to feminine values, in comparison to the masculine perspective, is a sign of commitment rather than rights, a collective social group rather than the individual and of an ethic based on caring for others rather than the traditional rationalistic arguments. Because of this, the introduction of qualitative diversity within this professional field is an important fact to highlight when women contribute to the engineering community through the enrichment, expansion and transformation of the values and attitudes that are predominant in the people who work and/or study within the area of engineering and technology.

A web-based translation service at the UOC based on Apertium

In this paper, we describe the adaptation process of Apertium, a free/open-source rule-based machine translation platform which is operating in a number of different real-life contexts, to the linguistic needs of the Universitat Oberta de Catalunya (Open University of Catalonia, UOC), a private e-learning university based in Barcelona where linguistic and cultural diversity is a crucial factor. This paper describes the main features of the Apertium platform and the practical developments required to fully adapt it to UOCs linguistic needs. The settting up of a translation service at UOC based on Apertium shows the growing interest of large institutions with translation needs for open-source solutions in which their investment is oriented toward adding value to the available features to offer the best possible adapted service to their user community.

Person Verification by Fusion of Prosodic, Voice Spectral and Facial Parameters.

This work has been partially supported by the European Union (under CHIL IST-2002-506909 and BIOSEC IST-2002-001766) and by the Spanish Government (under ACESCA project TIN2005-08852 and grant AP2003-3598).

Voice Disguise in Automatic Speaker Recognition

Humans are able to identify other people’s voices even in voice disguise conditions. However, we are not immune to all voice changes when trying to identify people from voice. Likewise, automatic speaker recognition systems can also be deceived by voice imitation and other types of disguise. Taking into account the voice disguise classification into the combination of two different categories (deliberate/non-deliberate and electronic/non-electronic), this survey provides a literature review on the influence of voice disguise in the automatic speaker recognition task and the robustness of these systems to such voice changes. Additionally, the survey addresses existing applications dealing with voice disguise and analyzes some issues for future research.