The infinite HMM for unsupervised PoS tagging

We extend previous work on fully unsupervised part-of-speech tagging. Using a non-parametric version of the HMM, called the infinite HMM (iHMM), we address the problem of choosing the number of hidden states in unsupervised Markov models for PoS tagging. We experiment with two non-parametric priors, the Dirichlet and Pitman-Yor processes, on the Wall Street Journal dataset using a parallelized implementation of an iHMM inference algorithm. We evaluate the results with a variety of clustering evaluation metrics and achieve equivalent or better performances than previously reported. Building on this promising result we evaluate the output of the unsupervised PoS tagger as a direct replacement for the output of a fully supervised PoS tagger for the task of shallow parsing and compare the two evaluations. © 2009 ACL and AFNLP.

A fuzzified systematic adjustment of the robotic Darwinian PSO

The Darwinian Particle Swarm Optimization (DPSO) is an evolutionary algorithm that extends the Particle Swarm Optimization using natural selection to enhance the ability to escape from sub-optimal solutions. An extension of the DPSO to multi-robot applications has been recently proposed and denoted as Robotic Darwinian PSO (RDPSO), benefiting from the dynamical partitioning of the whole population of robots, hence decreasing the amount of required information exchange among robots. This paper further extends the previously proposed algorithm adapting the behavior of robots based on a set of context-based evaluation metrics. Those metrics are then used as inputs of a fuzzy system so as to systematically adjust the RDPSO parameters (i.e., outputs of the fuzzy system), thus improving its convergence rate, susceptibility to obstacles and communication constraints. The adapted RDPSO is evaluated in groups of physical robots, being further explored using larger populations of simulated mobile robots within a larger scenario.

A Framework of Statistical Machine Translator from English to Malayalam

In this paper we describe the methodology and the structural design of a system that translates English into Malayalam using statistical models. A monolingual Malayalam corpus and a bilingual English/Malayalam corpus are the main resource in building this Statistical Machine Translator. Training strategy adopted has been enhanced by PoS tagging which helps to get rid of the insignificant alignments. Moreover, incorporating units like suffix separator and the stop word eliminator has proven to be effective in bringing about better training results. In the decoder, order conversion rules are applied to reduce the structural difference between the language pair. The quality of statistical outcome of the decoder is further improved by applying mending rules. Experiments conducted on a sample corpus have generated reasonably good Malayalam translations and the results are verified with F measure, BLEU and WER evaluation metrics

English to Malayalam Translation: A Statistical Approach

This paper underlines a methodology for translating text from English into the Dravidian language, Malayalam using statistical models. By using a monolingual Malayalam corpus and a bilingual English/Malayalam corpus in the training phase, the machine automatically generates Malayalam translations of English sentences. This paper also discusses a technique to improve the alignment model by incorporating the parts of speech information into the bilingual corpus. Removing the insignificant alignments from the sentence pairs by this approach has ensured better training results. Pre-processing techniques like suffix separation from the Malayalam corpus and stop word elimination from the bilingual corpus also proved to be effective in training. Various handcrafted rules designed for the suffix separation process which can be used as a guideline in implementing suffix separation in Malayalam language are also presented in this paper. The structural difference between the English Malayalam pair is resolved in the decoder by applying the order conversion rules. Experiments conducted on a sample corpus have generated reasonably good Malayalam translations and the results are verified with F measure, BLEU and WER evaluation metrics

A framework for translating English text into Malayalam using statistical models

A methodology for translating text from English into the Dravidian language, Malayalam using statistical models is discussed in this paper. The translator utilizes a monolingual Malayalam corpus and a bilingual English/Malayalam corpus in the training phase and generates automatically the Malayalam translation of an unseen English sentence. Various techniques to improve the alignment model by incorporating the morphological inputs into the bilingual corpus are discussed. Removing the insignificant alignments from the sentence pairs by this approach has ensured better training results. Pre-processing techniques like suffix separation from the Malayalam corpus and stop word elimination from the bilingual corpus also proved to be effective in producing better alignments. Difficulties in translation process that arise due to the structural difference between the English Malayalam pair is resolved in the decoding phase by applying the order conversion rules. The handcrafted rules designed for the suffix separation process which can be used as a guideline in implementing suffix separation in Malayalam language are also presented in this paper. Experiments conducted on a sample corpus have generated reasonably good Malayalam translations and the results are verified with F measure, BLEU and WER evaluation metrics

Extension schemes for the Alignment Model of English-Malayalam Statistical Machine Translator

In Statistical Machine Translation from English to Malayalam, an unseen English sentence is translated into its equivalent Malayalam sentence using statistical models. A parallel corpus of English-Malayalam is used in the training phase. Word to word alignments has to be set among the sentence pairs of the source and target language before subjecting them for training. This paper deals with certain techniques which can be adopted for improving the alignment model of SMT. Methods to incorporate the parts of speech information into the bilingual corpus has resulted in eliminating many of the insignificant alignments. Also identifying the name entities and cognates present in the sentence pairs has proved to be advantageous while setting up the alignments. Presence of Malayalam words with predictable translations has also contributed in reducing the insignificant alignments. Moreover, reduction of the unwanted alignments has brought in better training results. Experiments conducted on a sample corpus have generated reasonably good Malayalam translations and the results are verified with F measure, BLEU and WER evaluation metrics.

Techniques to Improve the word alignments in Statistical Machine Translation from English to Malayalam

In Statistical Machine Translation from English to Malayalam, an unseen English sentence is translated into its equivalent Malayalam translation using statistical models like translation model, language model and a decoder. A parallel corpus of English-Malayalam is used in the training phase. Word to word alignments has to be set up among the sentence pairs of the source and target language before subjecting them for training. This paper is deals with the techniques which can be adopted for improving the alignment model of SMT. Incorporating the parts of speech information into the bilingual corpus has eliminated many of the insignificant alignments. Also identifying the name entities and cognates present in the sentence pairs has proved to be advantageous while setting up the alignments. Moreover, reduction of the unwanted alignments has brought in better training results. Experiments conducted on a sample corpus have generated reasonably good Malayalam translations and the results are verified with F measure, BLEU and WER evaluation metrics

Evaluación de la ciencia y tecnología como instrumento de intervención del Estado en la Política Nacional de Ciencia, Tecnología e Innovación

El uso de instrumentos y directrices en la política pública para la modelación de los resultados de la actividad científica y tecnológica ha sido frecuente en el Estado colombiano. Este trabajo bajo la ‘teoría de la regulación’ de Black, examina el Modelo de Medición de Grupos de Investigación y de calificación de Revistas Científicas –Publindex- de Colciencias, como instrumentos de intervención del Estado, fundados en el uso de indicadores bibliométricos y cienciométricos. Para ello, se da respuesta a interrogantes referidos a la auto-organización de la ciencia; su relación con el Modelo de Grupos de Investigación, la influencia que dicho modelo tiene sobre la libertad de investigación; las implicaciones que tiene el otorgar categoría o status a los Grupos por actos estatales y la conveniencia de que el Estado tenga un sistema de incentivos para el examen de información científica y técnica originada en indicadores científicos, entre otros. Se busca en síntesis, aportar elementos que permitan, desde una perspectiva sistémica e interdisciplinaria explicar algunas de las razones por las cuales los elementos involucrados en la estructuración de la normativa de ciencia y tecnología, pueden inducir a afectaciones negativas y positivas en el quehacer científico y tecnológico.

ATD: a multiplatform for semiautomatic 3-D detection of kidneys and their pathology in real time

This research presents a novel multi-functional system for medical Imaging-enabled Assistive Diagnosis (IAD). Although the IAD demonstrator has focused on abdominal images and supports the clinical diagnosis of kidneys using CT/MRI imaging, it can be adapted to work on image delineation, annotation and 3D real-size volumetric modelling of other organ structures such as the brain, spine, etc. The IAD provides advanced real-time 3D visualisation and measurements with fully automated functionalities as developed in two stages. In the first stage, via the clinically driven user interface, specialist clinicians use CT/MRI imaging datasets to accurately delineate and annotate the kidneys and their possible abnormalities, thus creating “3D Golden Standard Models”. Based on these models, in the second stage, clinical support staff i.e. medical technicians interactively define model-based rules and parameters for the integrated “Automatic Recognition Framework” to achieve results which are closest to that of the clinicians. These specific rules and parameters are stored in “Templates” and can later be used by any clinician to automatically identify organ structures i.e. kidneys and their possible abnormalities. The system also supports the transmission of these “Templates” to another expert for a second opinion. A 3D model of the body, the organs and their possible pathology with real metrics is also integrated. The automatic functionality was tested on eleven MRI datasets (comprising of 286 images) and the 3D models were validated by comparing them with the metrics from the corresponding “3D Golden Standard Models”. The system provides metrics for the evaluation of the results, in terms of Accuracy, Precision, Sensitivity, Specificity and Dice Similarity Coefficient (DSC) so as to enable benchmarking of its performance. The first IAD prototype has produced promising results as its performance accuracy based on the most widely deployed evaluation metric, DSC, yields 97% for the recognition of kidneys and 96% for their abnormalities; whilst across all the above evaluation metrics its performance ranges between 96% and 100%. Further development of the IAD system is in progress to extend and evaluate its clinical diagnostic support capability through development and integration of additional algorithms to offer fully computer-aided identification of other organs and their abnormalities based on CT/MRI/Ultra-sound Imaging.

Complex networks analysis of manual and machine translations

Complex networks have been increasingly used in text analysis, including in connection with natural language processing tools, as important text features appear to be captured by the topology and dynamics of the networks. Following previous works that apply complex networks concepts to text quality measurement, summary evaluation, and author characterization, we now focus on machine translation (MT). In this paper we assess the possible representation of texts as complex networks to evaluate cross-linguistic issues inherent in manual and machine translation. We show that different quality translations generated by NIT tools can be distinguished from their manual counterparts by means of metrics such as in-(ID) and out-degrees (OD), clustering coefficient (CC), and shortest paths (SP). For instance, we demonstrate that the average OD in networks of automatic translations consistently exceeds the values obtained for manual ones, and that the CC values of source texts are not preserved for manual translations, but are for good automatic translations. This probably reflects the text rearrangements humans perform during manual translation. We envisage that such findings could lead to better NIT tools and automatic evaluation metrics.

Uma metodologia para modelagem e avaliação da dependabilidade de redes industriais sem fio

Ensuring the dependability requirements is essential for the industrial applications since faults may cause failures whose consequences result in economic losses, environmental damage or hurting people. Therefore, faced from the relevance of topic, this thesis proposes a methodology for the dependability evaluation of industrial wireless networks (WirelessHART, ISA100.11a, WIA-PA) on early design phase. However, the proposal can be easily adapted to maintenance and expansion stages of network. The proposal uses graph theory and fault tree formalism to create automatically an analytical model from a given wireless industrial network topology, where the dependability can be evaluated. The evaluation metrics supported are the reliability, availability, MTTF (mean time to failure), importance measures of devices, redundancy aspects and common cause failures. It must be emphasized that the proposal is independent of any tool to evaluate quantitatively the target metrics. However, due to validation issues it was used a tool widely accepted on academy for this purpose (SHARPE). In addition, an algorithm to generate the minimal cut sets, originally applied on graph theory, was adapted to fault tree formalism to guarantee the scalability of methodology in wireless industrial network environments (< 100 devices). Finally, the proposed methodology was validate from typical scenarios found in industrial environments, as star, line, cluster and mesh topologies. It was also evaluated scenarios with common cause failures and best practices to guide the design of an industrial wireless network. For guarantee scalability requirements, it was analyzed the performance of methodology in different scenarios where the results shown the applicability of proposal for networks typically found in industrial environments

Identidade das Ciências Humanas e métricas de avaliação: qualis periódicos e classificação de livros

This article aims to discuss the evaluation metrics adopted by Capes in the evaluation process of national graduate programs in the field of the Human Sciences, especially with respect to the classifications of scientific journals and books.

Algorithmen zur labelfreien quantitativen Proteomanalyse auf Basis datenunabhängig-akquirierter LC-MS-Daten

Moderne ESI-LC-MS/MS-Techniken erlauben in Verbindung mit Bottom-up-Ansätzen eine qualitative und quantitative Charakterisierung mehrerer tausend Proteine in einem einzigen Experiment. Für die labelfreie Proteinquantifizierung eignen sich besonders datenunabhängige Akquisitionsmethoden wie MSE und die IMS-Varianten HDMSE und UDMSE. Durch ihre hohe Komplexität stellen die so erfassten Daten besondere Anforderungen an die Analysesoftware. Eine quantitative Analyse der MSE/HDMSE/UDMSE-Daten blieb bislang wenigen kommerziellen Lösungen vorbehalten. rn| In der vorliegenden Arbeit wurden eine Strategie und eine Reihe neuer Methoden zur messungsübergreifenden, quantitativen Analyse labelfreier MSE/HDMSE/UDMSE-Daten entwickelt und als Software ISOQuant implementiert. Für die ersten Schritte der Datenanalyse (Featuredetektion, Peptid- und Proteinidentifikation) wird die kommerzielle Software PLGS verwendet. Anschließend werden die unabhängigen PLGS-Ergebnisse aller Messungen eines Experiments in einer relationalen Datenbank zusammengeführt und mit Hilfe der dedizierten Algorithmen (Retentionszeitalignment, Feature-Clustering, multidimensionale Normalisierung der Intensitäten, mehrstufige Datenfilterung, Proteininferenz, Umverteilung der Intensitäten geteilter Peptide, Proteinquantifizierung) überarbeitet. Durch diese Nachbearbeitung wird die Reproduzierbarkeit der qualitativen und quantitativen Ergebnisse signifikant gesteigert.rn| Um die Performance der quantitativen Datenanalyse zu evaluieren und mit anderen Lösungen zu vergleichen, wurde ein Satz von exakt definierten Hybridproteom-Proben entwickelt. Die Proben wurden mit den Methoden MSE und UDMSE erfasst, mit Progenesis QIP, synapter und ISOQuant analysiert und verglichen. Im Gegensatz zu synapter und Progenesis QIP konnte ISOQuant sowohl eine hohe Reproduzierbarkeit der Proteinidentifikation als auch eine hohe Präzision und Richtigkeit der Proteinquantifizierung erreichen.rn| Schlussfolgernd ermöglichen die vorgestellten Algorithmen und der Analyseworkflow zuverlässige und reproduzierbare quantitative Datenanalysen. Mit der Software ISOQuant wurde ein einfaches und effizientes Werkzeug für routinemäßige Hochdurchsatzanalysen labelfreier MSE/HDMSE/UDMSE-Daten entwickelt. Mit den Hybridproteom-Proben und den Bewertungsmetriken wurde ein umfassendes System zur Evaluierung quantitativer Akquisitions- und Datenanalysesysteme vorgestellt.

Combining statistical and semantic approaches to the translation of ontologies and taxonomies

Ontologies and taxonomies are widely used to organize concepts providing the basis for activities such as indexing, and as background knowledge for NLP tasks. As such, translation of these resources would prove useful to adapt these systems to new languages. However, we show that the nature of these resources is significantly different from the "free-text" paradigm used to train most statistical machine translation systems. In particular, we see significant differences in the linguistic nature of these resources and such resources have rich additional semantics. We demonstrate that as a result of these linguistic differences, standard SMT methods, in particular evaluation metrics, can produce poor performance. We then look to the task of leveraging these semantics for translation, which we approach in three ways: by adapting the translation system to the domain of the resource; by examining if semantics can help to predict the syntactic structure used in translation; and by evaluating if we can use existing translated taxonomies to disambiguate translations. We present some early results from these experiments, which shed light on the degree of success we may have with each approach

Programming assignments automatic grading: review of tools and implementations

Automatic grading of programming assignments is an important topic in academic research. It aims at improving the level of feedback given to students and optimizing the professor time. Several researches have reported the development of software tools to support this process. Then, it is helpfulto get a quickly and good sight about their key features. This paper reviews an ample set of tools forautomatic grading of programming assignments. They are divided in those most important mature tools, which have remarkable features; and those built recently, with new features. The review includes the definition and description of key features e.g. supported languages, used technology, infrastructure, etc. The two kinds of tools allow making a temporal comparative analysis. This analysis infrastructure, etc. The two kinds of tools allow making a temporal comparative analysis. This analysis shows good improvements in this research field, these include security, more language support, plagiarism detection, etc. On the other hand, the lack of a grading model for assignments is identified as an important gap in the reviewed tools. Thus, a characterization of evaluation metrics to grade programming assignments is provided as first step to get a model. Finally new paths in this research field are proposed.