European primary pupils show their life to African peers

Since primary school pupils lack a common language, primary school pupils from Germany and Africa show a piece of their origin and of their daily live through simple drawings to their peers in a other, distant land. The teachers accompanying the exchange of these drawings communicated in natural language, but helped to transform what their pupils wanted to show by their drawing. Five students drawings are presented in order to explain and illustrate this exchange method.

Motor de recomendación construido sobre implicaciones

Este Trabajo Fin de Grado (TFG) tiene como objetivo la creación de un framework para su uso en sistemas de recomendación. Se ha realizado por dos personas en la modalidad de trabajo en equipo. Las tareas de este TFG están divididas en dos partes, una realizada conjuntamente y la otra de manera individual. La parte conjunta se centra en construir un sistema que sea capaz de, a partir de comentarios y opiniones sobre puntos de interés (POIs) y haciendo uso de la herramienta de procesamiento de lenguaje natural AlchemyAPI, construir contextos formales y contextos formales multivaluados. Para crear este último es necesario hacer uso de ontologías. El context formal multivaluado es el punto de partida de la segunda parte (individual), que consistirá en, haciendo uso del contexto multivaluado, obtener un conjunto de dependencias funcionales mediante la implementación en Java del algoritmo FDMine. Estas dependencias podrán ser usados en un motor de recomendación. El sistema se ha implementado como una aplicación web Java EE versión 6 y una API para trabajar con contextos formales multivaluados. Para el desarrollo web se han empleado tecnologías actuales como Spring y jQuery. Este proyecto se presenta como un trabajo inicial en el que se expondrán, además del sistema construido, diversos problemas relacionados con la creacion de conjuntos de datos validos. Por último, también se propondrán líneas para futuros TFGs.

Statistical Analysis of Text Summarization Evaluation

This dissertation applies statistical methods to the evaluation of automatic summarization using data from the Text Analysis Conferences in 2008-2011. Several aspects of the evaluation framework itself are studied, including the statistical testing used to determine significant differences, the assessors, and the design of the experiment. In addition, a family of evaluation metrics is developed to predict the score an automatically generated summary would receive from a human judge and its results are demonstrated at the Text Analysis Conference. Finally, variations on the evaluation framework are studied and their relative merits considered. An over-arching theme of this dissertation is the application of standard statistical methods to data that does not conform to the usual testing assumptions.

Trace Oblivious Program Execution

The big data era has dramatically transformed our lives; however, security incidents such as data breaches can put sensitive data (e.g. photos, identities, genomes) at risk. To protect users' data privacy, there is a growing interest in building secure cloud computing systems, which keep sensitive data inputs hidden, even from computation providers. Conceptually, secure cloud computing systems leverage cryptographic techniques (e.g., secure multiparty computation) and trusted hardware (e.g. secure processors) to instantiate a “secure” abstract machine consisting of a CPU and encrypted memory, so that an adversary cannot learn information through either the computation within the CPU or the data in the memory. Unfortunately, evidence has shown that side channels (e.g. memory accesses, timing, and termination) in such a “secure” abstract machine may potentially leak highly sensitive information, including cryptographic keys that form the root of trust for the secure systems. This thesis broadly expands the investigation of a research direction called trace oblivious computation, where programming language techniques are employed to prevent side channel information leakage. We demonstrate the feasibility of trace oblivious computation, by formalizing and building several systems, including GhostRider, which is a hardware-software co-design to provide a hardware-based trace oblivious computing solution, SCVM, which is an automatic RAM-model secure computation system, and ObliVM, which is a programming framework to facilitate programmers to develop applications. All of these systems enjoy formal security guarantees while demonstrating a better performance than prior systems, by one to several orders of magnitude.

Testu arteko koherentziazko erlazio-egitura: lehen urratsak euskaraz

[EU]Testu bat koherente egiten duten arrazoiak ulertzea oso baliagarria da testuaren beraren ulermenerako, koherentzia eta koherentzia-erlazioak testu bat edo gehiago koherente diren ondorioztatzen laguntzen baitigu. Lan honetan gai bera duten testu ezberdinen arteko koherentziazko 3 Cross Document Structure Theory edo CST (Radev, 2000) erlazio aztertu eta sailkatu dira. Hori egin ahal izateko, euskaraz idatziriko gai berari buruzko testuak segmentatzeko eta beraien arteko erlazioak etiketatzeko gidalerroak proposatzen dira. 10 testuz osaturiko corpusa etiketatu da; horietako 3 cluster bi etiketatzailek aztertu dute. Etiketatzaileen arteko adostasunaren berri ematen dugu. Koherentzia-erlazioak garatzea oso garrantzitsua da Hizkuntzaren Prozesamenduko hainbat sistementzat, hala nola, informazioa erauzteko sistementzat, itzulpen automatikoarentzat, galde-erantzun sistementzat eta laburpen automatikoarentzat. Etorkizunean CSTko erlazio guztiak corpus esanguratsuan aztertuko balira, testuen arteko koherentzia- erlazioak euskarazko testuen prozesaketa automatikoa bideratzeko lehenengo pausua litzateke hemen egindakoa.

Lexicon-grammar of Russian verbal idioms

Dissertação de Mestrado, Ciências da Linguagem, Faculdade de Ciências Humanas e Sociais, Universidade do Algarve, 2016

A novel concept-level approach for ultra-concise opinion summarization

The Web 2.0 has resulted in a shift as to how users consume and interact with the information, and has introduced a wide range of new textual genres, such as reviews or microblogs, through which users communicate, exchange, and share opinions. The exploitation of all this user-generated content is of great value both for users and companies, in order to assist them in their decision-making processes. Given this context, the analysis and development of automatic methods that can help manage online information in a quicker manner are needed. Therefore, this article proposes and evaluates a novel concept-level approach for ultra-concise opinion abstractive summarization. Our approach is characterized by the integration of syntactic sentence simplification, sentence regeneration and internal concept representation into the summarization process, thus being able to generate abstractive summaries, which is one the most challenging issues for this task. In order to be able to analyze different settings for our approach, the use of the sentence regeneration module was made optional, leading to two different versions of the system (one with sentence regeneration and one without). For testing them, a corpus of 400 English texts, gathered from reviews and tweets belonging to two different domains, was used. Although both versions were shown to be reliable methods for generating this type of summaries, the results obtained indicate that the version without sentence regeneration yielded to better results, improving the results of a number of state-of-the-art systems by 9%, whereas the version with sentence regeneration proved to be more robust to noisy data.

Chebanov law and Vakar formula in mathematical models of complex systems

Ecological models written in a mathematical language L(M) or model language, with a given style or methodology can be considered as a text. It is possible to apply statistical linguistic laws and the experimental results demonstrate that the behaviour of a mathematical model is the same of any literary text of any natural language. A text has the following characteristics: (a) the variables, its transformed functions and parameters are the lexic units or LUN of ecological models; (b) the syllables are constituted by a LUN, or a chain of them, separated by operating or ordering LUNs; (c) the flow equations are words; and (d) the distribution of words (LUM and CLUN) according to their lengths is based on a Poisson distribution, the Chebanov's law. It is founded on Vakar's formula, that is calculated likewise the linguistic entropy for L(M). We will apply these ideas over practical examples using MARIOLA model. In this paper it will be studied the problem of the lengths of the simple lexic units composed lexic units and words of text models, expressing these lengths in number of the primitive symbols, and syllables. The use of these linguistic laws renders it possible to indicate the degree of information given by an ecological model.

Learning data-driven models of non-verbal behaviors for building rapport using an intelligent virtual agent

There is a growing societal need to address the increasing prevalence of behavioral health issues, such as obesity, alcohol or drug use, and general lack of treatment adherence for a variety of health problems. The statistics, worldwide and in the USA, are daunting. Excessive alcohol use is the third leading preventable cause of death in the United States (with 79,000 deaths annually), and is responsible for a wide range of health and social problems. On the positive side though, these behavioral health issues (and associated possible diseases) can often be prevented with relatively simple lifestyle changes, such as losing weight with a diet and/or physical exercise, or learning how to reduce alcohol consumption. Medicine has therefore started to move toward finding ways of preventively promoting wellness, rather than solely treating already established illness.^ Evidence-based patient-centered Brief Motivational Interviewing (BMI) interventions have been found particularly effective in helping people find intrinsic motivation to change problem behaviors after short counseling sessions, and to maintain healthy lifestyles over the long-term. Lack of locally available personnel well-trained in BMI, however, often limits access to successful interventions for people in need. To fill this accessibility gap, Computer-Based Interventions (CBIs) have started to emerge. Success of the CBIs, however, critically relies on insuring engagement and retention of CBI users so that they remain motivated to use these systems and come back to use them over the long term as necessary.^ Because of their text-only interfaces, current CBIs can therefore only express limited empathy and rapport, which are the most important factors of health interventions. Fortunately, in the last decade, computer science research has progressed in the design of simulated human characters with anthropomorphic communicative abilities. Virtual characters interact using humans’ innate communication modalities, such as facial expressions, body language, speech, and natural language understanding. By advancing research in Artificial Intelligence (AI), we can improve the ability of artificial agents to help us solve CBI problems.^ To facilitate successful communication and social interaction between artificial agents and human partners, it is essential that aspects of human social behavior, especially empathy and rapport, be considered when designing human-computer interfaces. Hence, the goal of the present dissertation is to provide a computational model of rapport to enhance an artificial agent’s social behavior, and to provide an experimental tool for the psychological theories shaping the model. Parts of this thesis were already published in [LYL+12, AYL12, AL13, ALYR13, LAYR13, YALR13, ALY14].^

Modelling the generation of customised poetry in Jess

The present paper presents an application that composes formal poetry in Spanish in a semiautomatic interactive fashion. JASPER is a forward reasoning rule-based system that obtains from the user an intended message, the desired metric, a choice of vocabulary, and a corpus of verses; and, by intelligent adaptation of selected examples from this corpus using the given words, carries out a prose-to-poetry translation of the given message. In the composition process, JASPER combines natural language generation and a set of construction heuristics obtained from formal literature on Spanish poetry.

Knowledge and writing in school mathematics : a communicational approach

This thesis is about young students’ writing in school mathematics and the ways in which this writing is designed, interpreted and understood. Students’ communication can act as a source from which teachers can make inferences regarding students’ mathematical knowledge and understanding. In mathematics education previous research indicates that teachers assume that the process of interpreting and judging students’ writing is unproblematic. The relationship between what students’ write, and what they know or understand, is theoretical as well as empirical. In an era of increased focus on assessment and measurement in education it is necessary for teachers to know more about the relationship between communication and achievement. To add to this knowledge, the thesis has adopted a broad approach, and the thesis consists of four studies. The aim of these studies is to reach a deep understanding of writing in school mathematics. Such an understanding is dependent on examining different aspects of writing. The four studies together examine how the concept of communication is described in authoritative texts, how students’ writing is viewed by teachers and how students make use of different communicational resources in their writing. The results of the four studies indicate that students’ writing is more complex than is acknowledged by teachers and authoritative texts in mathematics education. Results point to a sophistication in students’ approach to the merging of the two functions of writing, writing for oneself and writing for others. Results also suggest that students attend, to various extents, to questions regarding how, what and for whom they are writing in school mathematics. The relationship between writing and achievement is dependent on students’ ability to have their writing reflect their knowledge and on teachers’ thorough knowledge of the different features of writing and their awareness of its complexity. From a communicational perspective the ability to communicate [in writing] in mathematics can and should be distinguished from other mathematical abilities. By acknowledging that mathematical communication integrates mathematical language and natural language, teachers have an opportunity to turn writing in mathematics into an object of learning. This offers teachers the potential to add to their assessment literacy and offers students the potential to develop their communicational ability in order to write in a way that better reflects their mathematical knowledge.

Reconhecimento de entidades mencionadas usando o Google

O Reconhecimento de Entidades Mencionadas tem como objectivo identificar e classificar entidades, baseando-se em determinadas categorias ou etiquetas, contidas em textos escritos em linguagem natural. O Sistema de Reconhecimento de Entidades Mencionadas implementado na elaboração desta Dissertação pretende identificar localidades presentes em textos informais e definir para cada localidade identificada uma das etiquetas “aldeia", "vila" ou “cidade" numa primeira aproximação ao problema. Numa segunda aproximação tiveram-se em conta as etiquetas "freguesia", "concelho" e "distrito". Para a obtenção das classificações das entidades procedeu-se a uma análise estatística do número de resultados obtidos numa pesquisa de uma entidade precedida por uma etiqueta usando o motor de pesquisa Google Search. ABSTRACT: Named Entitity Recognition has the objective of identifying and classifying entities, according to certain categories or labels, contained in texts written in natural language. The Named Entitity Recognition system implemented in the developing of this dissertation intends to identify localities in informal texts, setting for each one of these localities identified one of the labels "aldeia", ''vila" or "cidade" in a first approach to the problem. ln a second approach the labels "freguesia", "concelho" and "distrito" were taken in consideration. To obtain classifications for the entities a statistical analysis of the number of results returned by a search of an entity preceded by a label using Google search engine was performed.

Normalização automática de descrições de hotéis

As descrições de produtos turísticos na área da hotelaria, aviação, rent-a-car e pacotes de férias baseiam-se sobretudo em descrições textuais em língua natural muito heterogénea com estilos, apresentações e conteúdos muito diferentes entre si. Uma vez que o sector do turismo é bastante dinâmico e que os seus produtos e ofertas estão constantemente em alteração, o tratamento manual de normalização de toda essa informação não é possível. Neste trabalho construiu-se um protótipo que permite a classificação e extracção automática de informação a partir de descrições de produtos de turismo. Inicialmente a informação é classificada quanto ao tipo. Seguidamente são extraídos os elementos relevantes de cada tipo e gerados objectos facilmente computáveis. Sobre os objectos extraídos, o protótipo com recurso a modelos de textos e imagens gera automaticamente descrições normalizadas e orientadas a um determinado mercado. Esta versatilidade permite um novo conjunto de serviços na promoção e venda dos produtos que seria impossível implementar com a informação original. Este protótipo, embora possa ser aplicado a outros domínios, foi avaliado na normalização da descrição de hotéis. As frases descritivas do hotel são classificadas consoante o seu tipo (Local, Serviços e/ou Equipamento) através de um algoritmo de aprendizagem automática que obtém valores médios de cobertura de 96% e precisão de 72%. A cobertura foi considerada a medida mais importante uma vez que a sua maximização permite que não se percam frases para processamentos posteriores. Este trabalho permitiu também a construção e população de uma base de dados de hotéis que possibilita a pesquisa de hotéis pelas suas características. Esta funcionalidade não seria possível utilizando os conteúdos originais. ABSTRACT: The description of tourism products, like hotel, aviation, rent-a-car and holiday packages, is strongly supported on natural language expressions. Due to the extent of tourism offers and considering the high dynamics in the tourism sector, manual data management is not a reliable or scalable solution. Offer descriptions - in the order of thousands - are structured in different ways, possibly comprising different languages, complementing and/or overlap one another. This work aims at creating a prototype for the automatic classification and extraction of relevant knowledge from tourism-related text expressions. Captured knowledge is represented in a normalized/standard format to enable new services based on this information in order to promote and sale tourism products that would be impossible to implement with the raw information. Although it could be applied to other areas, this prototype was evaluated in the normalization of hotel descriptions. Hotels descriptive sentences are classified according their type (Location, Services and/or Equipment) using a machine learning algorithm. The built setting obtained an average recall of 96% and precision of 72%. Recall considered the most important measure of performance since its maximization allows that sentences were not lost in further processes. As a side product a database of hotels was built and populated with search facilities on its characteristics. This ability would not be possible using the original contents.

Medical semantic similarity with a neural language model

Advances in neural network language models have demonstrated that these models can effectively learn representations of words meaning. In this paper, we explore a variation of neural language models that can learn on concepts taken from structured ontologies and extracted from free-text, rather than directly from terms in free-text. This model is employed for the task of measuring semantic similarity between medical concepts, a task that is central to a number of techniques in medical informatics and information retrieval. The model is built with two medical corpora (journal abstracts and patient records) and empirically validated on two ground-truth datasets of human-judged concept pairs assessed by medical professionals. Empirically, our approach correlates closely with expert human assessors ($\approx$ 0.9) and outperforms a number of state-of-the-art benchmarks for medical semantic similarity. The demonstrated superiority of this model for providing an effective semantic similarity measure is promising in that this may translate into effectiveness gains for techniques in medical information retrieval and medical informatics (e.g., query expansion and literature-based discovery).

Natural actor and belief critic: Reinforcement algorithm for learning parameters of dialogue systems modelled as POMDPs

This article presents a novel algorithm for learning parameters in statistical dialogue systems which are modeled as Partially Observable Markov Decision Processes (POMDPs). The three main components of a POMDP dialogue manager are a dialogue model representing dialogue state information; a policy that selects the system's responses based on the inferred state; and a reward function that specifies the desired behavior of the system. Ideally both the model parameters and the policy would be designed to maximize the cumulative reward. However, while there are many techniques available for learning the optimal policy, no good ways of learning the optimal model parameters that scale to real-world dialogue systems have been found yet. The presented algorithm, called the Natural Actor and Belief Critic (NABC), is a policy gradient method that offers a solution to this problem. Based on observed rewards, the algorithm estimates the natural gradient of the expected cumulative reward. The resulting gradient is then used to adapt both the prior distribution of the dialogue model parameters and the policy parameters. In addition, the article presents a variant of the NABC algorithm, called the Natural Belief Critic (NBC), which assumes that the policy is fixed and only the model parameters need to be estimated. The algorithms are evaluated on a spoken dialogue system in the tourist information domain. The experiments show that model parameters estimated to maximize the expected cumulative reward result in significantly improved performance compared to the baseline hand-crafted model parameters. The algorithms are also compared to optimization techniques using plain gradients and state-of-the-art random search algorithms. In all cases, the algorithms based on the natural gradient work significantly better. © 2011 ACM.