An intelligent sales assistant for configurable products

Some of the recent proposals of web-based applications are oriented to provide advanced search services through virtual shops. Within this context, this paper proposes an advanced type of software application that simulates how a sales assistant dialogues with a consumer to dynamically configure a product according to particular needs. The paper presents the general knowl- edge model that uses artificial intelligence and knowledge-based techniques to simulate the configuration process. Finally, the paper illustrates the description with an example of an application in the field of photography equipment.

Estimating Adaptacion of Dialogue Partners with Different Verbal Intelligence

This work investigates to what degree speakers with different verbal intelligence may adapt to each other. The work is based on a corpus consisting of 100 descriptions of a short film (monologues), 56 discussions about the same topic (dialogues), and verbal intelligence scores of the test participants. Adaptation between two dialogue partners was measured using cross-referencing, proportion of "I", "You" and "We" words, between-subject correlation and similarity of texts. It was shown that lower verbal intelligence speakers repeated more nouns and adjectives from the other and used the same linguistic categories more often than higher verbal intelligence speakers. In dialogues between strangers, participants with higher verbal intelligence showed a greater level of adaptation.

Relating dominance of dialogue participants with their verbal intelligence scores

In this work we investigated whether there is a relationship between dominant behaviour of dialogue participants and their verbal intelligence. The analysis is based on a corpus containing 56 dialogues and verbal intelligence scores of the test persons. All the dialogues were divided into three groups: H-H is a group of dialogues between higher verbal intelligence participants, L-L is a group of dialogues between lower verbal intelligence participant and L-H is a group of all the other dialogues. The dominance scores of the dialogue partners from each group were analysed. The analysis showed that differences between dominance scores and verbal intelligence coefficients for L-L were positively correlated. Verbal intelligence scores of the test persons were compared to other features that may reflect dominant behaviour. The analysis showed that number of interruptions, long utterances, times grabbed the floor, influence diffusion model, number of agreements and several acoustic features may be related to verbal intelligence. These features were used for the automatic classification of the dialogue partners into two groups (lower and higher verbal intelligence participants); the achieved accuracy was 89.36%.

Adapting a speech into sign language translation system to a new domain

This paper presents a methodology for adapting an advanced communication system for deaf people in a new domain. This methodology is a user-centered design approach consisting of four main steps: requirement analysis, parallel corpus generation, technology adaptation to the new domain, and finally, system evaluation. In this paper, the new considered domain has been the dialogues in a hotel reception. With this methodology, it was possible to develop the system in a few months, obtaining very good performance: good speech recognition and translation rates (around 90%) with small processing times.

Servicios de redes sociales en internet para generación de consenso

En los últimos años, la cantidad de información que se ha generado en la web ha sido enorme. El tráfico que se está generando en la actualidad es de unos 16144 Gigabytes/s, pero se estima que para el 2019 será tres veces mayor, de unos 51794 Gigabytes/s (Cisco Systems, Inc, 2015). Esta ingente cantidad de tráfico viene sobre todo de vídeo, audio e imágenes, ya que estos son los contenidos que requieren más almacenamiento. En esta era de la información, si nos paramos a pensar por un segundo, nos podemos dar cuenta que donde realmente está esa información es en el texto. En la web hay muchísimo texto, pero no supone una gran cantidad de almacenamiento. Esto no quiere decir que lo podamos despreciar. Lo que tenemos que hacer es darle relevancia a todo ese texto, y hacer énfasis en lo importante. Esto es lo que podríamos hacer con herramientas de argumentación. La argumentación se refiere al estudio de las disconformidades, de los diálogos y los textos que usamos para intentar convencer a alguien de nuestro punto de vista. Por tanto, estas herramientas deberían de ser capaces de organizar un diálogo o discusión y obtener un resultado de esa conversación. Esto es muy normal en las discusiones habladas: discutimos para llegar a un acuerdo (o no), pero no es tan común en las discusiones online. En las discusiones online suele haber muchísimos comentarios, sin orden alguno, y sin conocer cuál es el acuerdo al que se ha llegado. Este trabajo hará una presentación de la argumentación y los modelos de argumentación: esquemas o estructuras a los cuales responde una discusión o un texto argumentativo. Así pues, nos centramos en las herramientas disponibles, ya que queremos conocer en qué estado se encuentran: si realmente ya hay herramientas que solucionen el problema organizativo o no. Por tanto, se presentan varias herramientas y se comparan en base al problema que existe utilizando ciertas características necesarias para el correcto funcionamiento de una de estas herramientas. Es ahí donde conoceremos si la herramienta que buscamos existe.---ABSTRACT---In recent years, the amount of Information generated on the web has been quite great. The traffic generated currently is approximately 16144 Gigabytes/s, but it is estimated that it will be three times larger by 2019, approximately 51794 Gigabytes/s (Cisco Systems, Inc, 2015). This huge amount of traffic comes mostly from multimedia (video, audio and images), as these kind of contents require more storage. This is the information era. If we think a bit about it, we can realize that this information is actually in the text. The web contains so much text, but it represents a small part of the whole storage. This does not mean that we can underestimate it. What we have to do is to give it relevance and emphasize what is important. This could be done by using argumentation tools. Argumentation refers to the study of agreement, disagreement, and of the dialogues and writing through which we convince others of our points of view. Therefore, these tools should be able to organize a dialogue or discussion and obtain from it an outcome or answer. It is common to obtain this outcome in spoken discussions: we discuss to reach an agreement (or not), however it is not really common in online discussions. In online discussions, they tend to have a huge amount of comments, with no order, and without knowing the outcome that has been reached. This thesis will explain the argumentation and the argumentation models: schemes or structures which a discussion or argumentative text respond to. Knowing this, we will focus on the available tools, because we want to know their state: whether there already are tools which can solve the organizational problem or not. Therefore, several tools are presented and compared based on this problem using some features that are needed for the proper functioning of these tools. This is where we will know whether the tool we are looking for exists or not.

Methodology for developing an advanced communications system for the Deaf in a new domain

A methodology for developing an advanced communications system for the Deaf in a new domain is presented in this paper. This methodology is a user-centred design approach consisting of four main steps: requirement analysis, parallel corpus generation, technology adaptation to the new domain, and finally, system evaluation. During the requirement analysis, both the user and technical requirements are evaluated and defined. For generating the parallel corpus, it is necessary to collect Spanish sentences in the new domain and translate them into LSE (Lengua de Signos Española: Spanish Sign Language). LSE is represented by glosses and using video recordings. This corpus is used for training the two main modules of the advanced communications system to the new domain: the spoken Spanish into the LSE translation module and the Spanish generation from the LSE module. The main aspects to be generated are the vocabularies for both languages (Spanish words and signs), and the knowledge for translating in both directions. Finally, the field evaluation is carried out with deaf people using the advanced communications system to interact with hearing people in several scenarios. In this evaluation, the paper proposes several objective and subjective measurements for evaluating the performance. In this paper, the new considered domain is about dialogues in a hotel reception. Using this methodology, the system was developed in several months, obtaining very good performance: good translation rates (10% Sign Error Rate) with small processing times, allowing face-to-face dialogues.

El fragmento y la abstracción

El tema objeto de esta Tesis, el Fragmento y la Abstracción, es una propuesta de análisis sobre el diálogo entre el fragmento como object trouvé y la abstracción, como un modo de proceder por parte del autor en el proyecto de arquitectura. En un principio, tal vez la creación artística nació como un intento por comprender la complejidad del mundo en que el ser humano vivía. Y se dedica a establecer un diálogo con el fragmento, a veces buscando su significado como parte de una historia desconocida, otras como parte de su propia historia pero también como referencia a una etapa mítica, convirtiéndose en símbolo de un paraíso perdido. El fragmento ha dado lugar al diálogo entre obra y autor tanto en música como en literatura o pintura. Esta tesis intenta analizar dicho diálogo en la arquitectura. Esta investigación comienza interrogándose sobre el sentido del fragmento y la abstracción como el modo de pensamiento leve, en definición de Italo Calvino, que nos permite conectar las ideas más alejadas. Para ello, se propusieron cinco modelos para explorar dicha relación. Los edificios elegidos fueron 1.- Villa Adriana 2.- Palacio de Carlos V en la Alhambra 3.- La casa- museo de Sir John Soane 4.- El Carmen de Rodríguez-Acosta 5.- Castelvecchio Dos de ellos residencies imperiales (1 y 2) Dos fortalezas (2 y5) Dos casas-estudio (3 y 4) Las cinco tienen relación con jardines De sus autores no todos son conocidos Tres de ellos se dedicaron a la docencia en arquitectura. Los cinco tienen carácter museográfico. P.D. Durante la investigación, para relacionar a unos y otros, se introdujo a Gian Battista Piranesi como importante nexo de unión entre antigüedad y modernidad. ABSTRACT The subject of this Thesis “Fragment and Abstraction, is a purpose of analysis about the dialogue between fragment as object trouvé and abstraction, as a way to do by the author in the architectural project. At first, we suppose historically that artistic creation is born as a way to understand the complexity of the world where the human beings lives. They tried to stablish a dialogue with the fragment, looking for its meaning, sometimes as the part of an unknown story, sometimes as part of their own history, but sometimes as reference of mythic times, becoming a symbol of a lost paradise. In arts, fragment is at beginning of many dialogues between craft and the author, as we know in music, literature or painting. This thesis try to analyze this dialogue in architecture. This investigation began asking for the meaning of fragment as something what was broken out from something we do not know, and abstraction as an immaterial way of thinking which let us connecting the most far ideas. Therefore, five architectural model were proposed, in order to explain that relationship. The chosen buildings were: 1- Villa Adriana 2- Charles V Imperator’s Palace at la Alhambra 3- Sir John Soane House -Museum 4- Rodríguez –Acostas’s Carmen 5- Castelvecchio by Carlo Scarpa There are: Two Imperial palaces (the 1st and 2nd), Two fortresses (the 2nd and 5th) Two House-Artist Studio (the 3rd and 4th) Five types of relationship with gardens. The authors, from them, we do not know some of them Three of the architects used to teach architecture All of them went to Rome Now the five buildings have become museum institution.During the investigation, in order to explain the relationship between them, I introduced Giambattista Piranesi as an important nexus to understand the transition from the antiquity to the modernity.