Automatic rule induction in Arabic to English machine translation framework

This chapter addresses the exploitation of a supervised machine learning technique to automatically induce Arabic-to-English transfer rules from chunks of parallel aligned linguistic resources. The induced structural transfer rules encode the linguistic translation knowledge for converting an Arabic syntactic structure into a target English syntactic structure. These rules are going to be an integral part of an Arabic-English transfer-based machine translation. Nevertheless, a novel morphological rule induction method is employed for learning Arabic morphological rules that are applied in our Arabic morphological analyzer. To demonstrate the capability of the automated rule induction technique, we conducted rule-based translation experiments that use induced rules from a relatively small data set. The translation quality of the hybrid translation experiments achieved good results in terms of WER.

Automatic Categorization for Improving Spanish into Spanish Sign Language Machine Translation

This paper describes a preprocessing module for improving the performance of a Spanish into Spanish Sign Language (Lengua de Signos Espanola: LSE) translation system when dealing with sparse training data. This preprocessing module replaces Spanish words with associated tags. The list with Spanish words (vocabulary) and associated tags used by this module is computed automatically considering those signs that show the highest probability of being the translation of every Spanish word. This automatic tag extraction has been compared to a manual strategy achieving almost the same improvement. In this analysis, several alternatives for dealing with non-relevant words have been studied. Non-relevant words are Spanish words not assigned to any sign. The preprocessing module has been incorporated into two well-known statistical translation architectures: a phrase-based system and a Statistical Finite State Transducer (SFST). This system has been developed for a specific application domain: the renewal of Identity Documents and Driver's License. In order to evaluate the system a parallel corpus made up of 4080 Spanish sentences and their LSE translation has been used. The evaluation results revealed a significant performance improvement when including this preprocessing module. In the phrase-based system, the proposed module has given rise to an increase in BLEU (Bilingual Evaluation Understudy) from 73.8% to 81.0% and an increase in the human evaluation score from 0.64 to 0.83. In the case of SFST, BLEU increased from 70.6% to 78.4% and the human evaluation score from 0.65 to 0.82.

Discriminative language model adaptation for Mandarin broadcast speech transcription and translation

This paper investigates unsupervised test-time adaptation of language models (LM) using discriminative methods for a Mandarin broadcast speech transcription and translation task. A standard approach to adapt interpolated language models to is to optimize the component weights by minimizing the perplexity on supervision data. This is a widely made approximation for language modeling in automatic speech recognition (ASR) systems. For speech translation tasks, it is unclear whether a strong correlation still exists between perplexity and various forms of error cost functions in recognition and translation stages. The proposed minimum Bayes risk (MBR) based approach provides a flexible framework for unsupervised LM adaptation. It generalizes to a variety of forms of recognition and translation error metrics. LM adaptation is performed at the audio document level using either the character error rate (CER), or translation edit rate (TER) as the cost function. An efficient parameter estimation scheme using the extended Baum-Welch (EBW) algorithm is proposed. Experimental results on a state-of-the-art speech recognition and translation system are presented. The MBR adapted language models gave the best recognition and translation performance and reduced the TER score by up to 0.54% absolute. © 2007 IEEE.

Automatic Detection of Relevant Head Gestures in American Sign Language Communication

An automated system for detection of head movements is described. The goal is to label relevant head gestures in video of American Sign Language (ASL) communication. In the system, a 3D head tracker recovers head rotation and translation parameters from monocular video. Relevant head gestures are then detected by analyzing the length and frequency of the motion signal's peaks and valleys. Each parameter is analyzed independently, due to the fact that a number of relevant head movements in ASL are associated with major changes around one rotational axis. No explicit training of the system is necessary. Currently, the system can detect "head shakes." In experimental evaluation, classification performance is compared against ground-truth labels obtained from ASL linguists. Initial results are promising, as the system matches the linguists' labels in a significant number of cases.

Safety-critical medical device development using the UPP2SF model translation tool

Software-based control of life-critical embedded systems has become increasingly complex, and to a large extent has come to determine the safety of the human being. For example, implantable cardiac pacemakers have over 80,000 lines of code which are responsible for maintaining the heart within safe operating limits. As firmware-related recalls accounted for over 41% of the 600,000 devices recalled in the last decade, there is a need for rigorous model-driven design tools to generate verified code from verified software models. To this effect, we have developed the UPP2SF model-translation tool, which facilitates automatic conversion of verified models (in UPPAAL) to models that may be simulated and tested (in Simulink/Stateflow). We describe the translation rules that ensure correct model conversion, applicable to a large class of models. We demonstrate how UPP2SF is used in themodel-driven design of a pacemaker whosemodel is (a) designed and verified in UPPAAL (using timed automata), (b) automatically translated to Stateflow for simulation-based testing, and then (c) automatically generated into modular code for hardware-level integration testing of timing-related errors. In addition, we show how UPP2SF may be used for worst-case execution time estimation early in the design stage. Using UPP2SF, we demonstrate the value of integrated end-to-end modeling, verification, code-generation and testing process for complex software-controlled embedded systems. © 2014 ACM.

Image to text translation by multi-label classification

This paper presents an image to text translation platform consisting of image segmentation, region features extraction, region blobs clustering, and translation components. A multi-label learning method is suggested for realizing the translation component. Empirical studies show that the predictive performance of the translation component is better than its counterparts when employed a dual-random ensemble multi-label classification algorithm.

Automatic code generation: from process algebraic architectural descriptions to multithreaded java programs

Process algebraic architectural description languages provide a formal means for modeling software systems and assessing their properties. In order to bridge the gap between system modeling and system im- plementation, in this thesis an approach is proposed for automatically generating multithreaded object-oriented code from process algebraic architectural descriptions, in a way that preserves – under certain assumptions – the properties proved at the architectural level. The approach is divided into three phases, which are illustrated by means of a running example based on an audio processing system. First, we develop an architecture-driven technique for thread coordination management, which is completely automated through a suitable package. Second, we address the translation of the algebraically-specified behavior of the individual software units into thread templates, which will have to be filled in by the software developer according to certain guidelines. Third, we discuss performance issues related to the suitability of synthesizing monitors rather than threads from software unit descriptions that satisfy specific constraints. In addition to the running example, we present two case studies about a video animation repainting system and the implementation of a leader election algorithm, in order to summarize the whole approach. The outcome of this thesis is the implementation of the proposed approach in a translator called PADL2Java and its integration in the architecture-centric verification tool TwoTowers.

Bitext alignment: building and evaluating a bilingual corpus and translation memory of academic course descriptions

Following the internationalization of contemporary higher education, academic institutions based in non-English speaking countries are increasingly urged to produce contents in English to address international prospective students and personnel, as well as to increase their attractiveness. The demand for English translations in the institutional academic domain is consequently increasing at a rate exceeding the capacity of the translation profession. Resources for assisting non-native authors and translators in the production of appropriate texts in L2 are therefore required in order to help academic institutions and professionals streamline their translation workload. Some of these resources include: (i) parallel corpora to train machine translation systems and multilingual authoring tools; and (ii) translation memories for computer-aided tools. The purpose of this study is to create and evaluate reference resources like the ones mentioned in (i) and (ii) through the automatic sentence alignment of a large set of Italian and English as a Lingua Franca (ELF) institutional academic texts given as equivalent but not necessarily parallel (i.e. translated). In this framework, a set of aligning algorithms and alignment tools is examined in order to identify the most profitable one(s) in terms of accuracy and time- and cost-effectiveness. In order to determine the text pairs to align, a sample is selected according to document length similarity (characters) and subsequently evaluated in terms of extent of noisiness/parallelism, alignment accuracy and content leverageability. The results of these analyses serve as the basis for the creation of an aligned bilingual corpus of academic course descriptions, which is eventually used to create a translation memory in TMX format.

A comparative study on manual and automatic slice-to-volume registration of CT images

In order to assess the clinical relevance of a slice-to-volume registration algorithm, this technique was compared to manual registration. Reformatted images obtained from a diagnostic CT examination of the lower abdomen were reviewed and manually registered by 41 individuals. The results were refined by the algorithm. Furthermore, a fully automatic registration of the single slices to the whole CT examination, without manual initialization, was also performed. The manual registration error for rotation and translation was found to be 2.7+/-2.8 degrees and 4.0+/-2.5 mm. The automated registration algorithm significantly reduced the registration error to 1.6+/-2.6 degrees and 1.3+/-1.6 mm (p = 0.01). In 3 of 41 (7.3%) registration cases, the automated registration algorithm failed completely. On average, the time required for manual registration was 213+/-197 s; automatic registration took 82+/-15 s. Registration was also performed without any human interaction. The resulting registration error of the algorithm without manual pre-registration was found to be 2.9+/-2.9 degrees and 1.1+/-0.2 mm. Here, a registration took 91+/-6 s, on average. Overall, the automated registration algorithm improved the accuracy of manual registration by 59% in rotation and 325% in translation. The absolute values are well within a clinically relevant range.

Discourse-level Annotation over Europarl for Machine Translation: Connectives and Pronouns

This paper describes methods and results for the annotation of two discourse-level phenomena, connectives and pronouns, over a multilingual parallel corpus. Excerpts from Europarl in English and French have been annotated with disambiguation information for connectives and pronouns, for about 3600 tokens. This data is then used in several ways: for cross-linguistic studies, for training automatic disambiguation software, and ultimately for training and testing discourse-aware statistical machine translation systems. The paper presents the annotation procedures and their results in detail, and overviews the first systems trained on the annotated resources and their use for machine translation.

Automatic exploitation of non-determinate independent and-parallelism in the basic andorra model

Andorra-I is the first implementation of a language based on the Andorra Principie, which states that determinate goals can (and shonld) be run before other goals, and even in a parallel fashion. This principie has materialized in a framework called the Basic Andorra model, which allows or-parallelism as well as (dependent) and-parallelism for determinate goals. In this report we show that it is possible to further extend this model in order to allow general independent and-parallelism for nondeterminate goals, withont greatly modifying the underlying implementation machinery. A simple an easy way to realize such an extensión is to make each (nondeterminate) independent goal determinate, by using a special "bagof" constract. We also show that this can be achieved antomatically by compile-time translation from original Prolog programs. A transformation that fulfüls this objective and which can be easily antomated is presented in this report.

Automatic motion compensation of free breathing acquired myocardial perfusion data by using independent component analysis

Images acquired during free breathing using first-pass gadolinium-enhanced myocardial perfusion magnetic resonance imaging (MRI) exhibit a quasiperiodic motion pattern that needs to be compensated for if a further automatic analysis of the perfusion is to be executed. In this work, we present a method to compensate this movement by combining independent component analysis (ICA) and image registration: First, we use ICA and a time?frequency analysis to identify the motion and separate it from the intensity change induced by the contrast agent. Then, synthetic reference images are created by recombining all the independent components but the one related to the motion. Therefore, the resulting image series does not exhibit motion and its images have intensities similar to those of their original counterparts. Motion compensation is then achieved by using a multi-pass image registration procedure. We tested our method on 39 image series acquired from 13 patients, covering the basal, mid and apical areas of the left heart ventricle and consisting of 58 perfusion images each. We validated our method by comparing manually tracked intensity profiles of the myocardial sections to automatically generated ones before and after registration of 13 patient data sets (39 distinct slices). We compared linear, non-linear, and combined ICA based registration approaches and previously published motion compensation schemes. Considering run-time and accuracy, a two-step ICA based motion compensation scheme that first optimizes a translation and then for non-linear transformation performed best and achieves registration of the whole series in 32 ± 12 s on a recent workstation. The proposed scheme improves the Pearsons correlation coefficient between manually and automatically obtained time?intensity curves from .84 ± .19 before registration to .96 ± .06 after registration