In the hearing-loss community, sign language is a primary tool to communicate with people while there is a communication gap between hearing-loss people with normal hearing people. Sign language is different from spoken language. It has its own vocabulary and grammar. Recent works concentrate on the sign language video caption which consists of sign language recognition and sign language translation. Continuous sign language recognition, which can bridge the communication gap, is a challenging task because of the weakly supervised ordered annotations where no frame-level label is provided. To overcome this problem, connectionist temporal classification (CTC) is the most widely used method. However, CTC learning could perform badly if the extracted features are not good. For better feature extraction, this thesis presents the novel self-attention-based fully-inception (SAFI) networks for vision-based end-to-end continuous sign language recognition. Considering the length of sign words differs from each other, we introduce the fully inception network with different receptive fields to extract dynamic clip-level features. To further boost the performance, the fully inception network with an auxiliary classifier is trained with aggregation cross entropy (ACE) loss. Then the encoder of self-attention networks as the global sequential feature extractor is used to model the clip-level features with CTC. The proposed model is optimized by jointly training with ACE on clip-level feature learning and CTC on global sequential feature learning in an end-to-end fashion. The best method in the baselines achieves 35.6% WER on the validation set and 34.5% WER on the test set. It employs a better decoding algorithm for generating pseudo labels to do the EM-like optimization to fine-tune the CNN module. In contrast, our approach focuses on the better feature extraction for end-to-end learning. To alleviate the overfitting on the limited dataset, we employ temporal elastic deformation to triple the real-world dataset RWTH- PHOENIX-Weather 2014. Experimental results on the real-world dataset RWTH- PHOENIX-Weather 2014 demonstrate the effectiveness of our approach which achieves 31.7% WER on the validation set and 31.2% WER on the test set. Even though sign language recognition can, to some extent, help bridge the communication gap, it is still organized in sign language grammar which is different from spoken language. Unlike sign language recognition that recognizes sign gestures, sign language translation (SLT) converts sign language to a target spoken language text which normal hearing people commonly use in their daily life. To achieve this goal, this thesis provides an effective sign language translation approach which gains state-of-the-art performance on the largest real-life German sign language translation database, RWTH-PHOENIX-Weather 2014T. Besides, a direct end-to-end sign language translation approach gives out promising results (an impressive gain from 9.94 to 13.75 BLEU and 9.58 to 14.07 BLEU on the validation set and test set) without intermediate recognition annotations. The comparative and promising experimental results show the feasibility of the direct end-to-end SLT

This dissertation addresses the problem of Machine Translation (MT), which is defined as an automated translation of a document written in one language (the source language) to another (the target language) by a computer. The MT task requires various types of knowledge of both the source and target language, e.g., linguistic rules and linguistic exceptions. Traditional MT systems rely on an extensive parsing strategy to decode the linguistic rules and use a knowledge base to encode those linguistic exceptions. However, the construction of the knowledge base becomes an issue as the translation system grows. To overcome this difficulty, real translation examples are used instead of a manually-crafted knowledge base. This design strategy is known as the Example-Based Machine Translation (EBMT) principle. Traditional EBMT systems utilize a database of word or phrase translation pairs. The main challenge of this approach is the difficulty of combining the word or phrase translation units into a meaningful and fluent target text. A novel Retrieval-Based Machine Translation (RBMT) system, which uses a sentence-level translation unit, is proposed in this study. An advantage of using the sentence-level translation unit is that the boundary of a sentence is explicitly defined and the semantic, or meaning, is precise in both the source and target language. The main challenge of using a sentential translation unit is the limited coverage, i.e., the difficulty of finding an exact match between a user query and sentences in the source database. Using an electronic dictionary and a topic modeling procedure, we develop a procedure to obtain clusters of sensible variations for each example in the source database. The coverage of our MT system improves because an input query text is matched against a cluster of sensible variations of translation examples instead of being matched against an original source example. In addition, pattern recognition techniques are used to improve the matching procedure, i.e., the design of optimal pattern classifiers and the incorporation of subjective judgments. A high performance statistical pattern classifier is used to identify the target sentences from an input query sentence in our MT system. The proposed classifier is different from the conventional classifier in terms of the way it addresses the generalization capability. A conventional classifier addresses the generalization issue using the parsimony principle and may encounter the possibility of choosing an oversimplified statistical model. The proposed classifier directly addresses the generalization issue in terms of training (empirical) data. Our classifier is expected to generalize better than the conventional classifiers because our classifier is less likely to use over-simplified statistical models based on the available training data. We further improve the matching procedure by the incorporation of subjective judgments. We formulate a novel cost function that combines subjective judgments and the degree of matching between translation examples and an input query. In addition, we provide an optimization strategy for the novel cost function so that the statistical model can be optimized according to the subjective judgments.

The quality of Machine Translation (MT) can often be poor due to it appearing incoherent and lacking in fluency. These problems consist of word ordering, awkward use of words and grammar, and translating text too literally. However we should not consider translations such as these failures until we have done our best to enhance their quality, or more simply, their fluency. In the same way various processes can be applied to touch up a photograph, various processes can also be applied to touch up a translation. This research outlines the improvement of MT quality through the application of Fluency Enhancement (FE), which is a process we have created that reforms and evaluates text to enhance its fluency. We have tested our FE process on our own MT system which operates on what we call the SAM fundamentals, which are as follows: Simplicity - to be simple in design in order to be portable across different languages pairs, Adaptability - to compensate for the evolution of language, and Multiplicity - to determine a final set of translations from as many candidate translations as possible. Based on our research, the SAM fundamentals are the key to developing a successful MT system, and are what have piloted the success of our FE process.

The quality of Machine Translation (MT) can often be poor due to it appearing incoherent and lacking in fluency. These problems consist of word ordering, awkward use of words and grammar, and translating text too literally. However we should not consider translations such as these failures until we have done our best to enhance their quality, or more simply, their fluency. In the same way various processes can be applied to touch up a photograph, various processes can also be applied to touch up a translation. This research outlines the improvement of MT quality through the application of Fluency Enhancement (FE), which is a process we have created that reforms and evaluates text to enhance its fluency. We have tested our FE process on our own MT system which operates on what we call the SAM fundamentals, which are as follows: Simplicity - to be simple in design in order to be portable across different languages pairs, Adaptability - to compensate for the evolution of language, and Multiplicity - to determine a final set of translations from as many candidate translations as possible. Based on our research, the SAM fundamentals are the key to developing a successful MT system, and are what have piloted the success of our FE process.

With the high cost of manually labeling data and the increasing interest in low-resource languages, for which human annotators might not be even available, unsupervised approaches have become essential for processing a typologically diverse set of languages, whether high-resource or low-resource. In this work, we propose new fully unsupervised approaches for two tasks in morphology: unsupervised morphological segmentation and unsupervised cross-lingual part-of-speech (POS) tagging, which have been two essential subtasks for several downstream NLP applications, such as machine translation, speech recognition, information extraction and question answering. We propose a new unsupervised morphological-segmentation approach that utilizes Adaptor Grammars (AGs), nonparametric Bayesian models that generalize probabilistic context-free grammars (PCFGs), where a PCFG models word structure in the task of morphological segmentation. We implement the approach as a publicly available morphological-segmentation framework, MorphAGram, that enables unsupervised morphological segmentation through the use of several proposed language-independent grammars. In addition, the framework allows for the use of scholar knowledge, when available, in the form of affixes that can be seeded into the grammars. The framework handles the cases when the scholar-seeded knowledge is either generated from language resources, possibly by someone who does not know the language, as weak linguistic priors, or generated by an expert in the underlying language as strong linguistic priors. Another form of linguistic priors is the design of a grammar that models language-dependent specifications. We also propose a fully unsupervised learning setting that approximates the effect of scholar-seeded knowledge through self-training. Moreover, since there is no single grammar that works best across all languages, we propose an approach that picks a nearly optimal configuration (a learning setting and a grammar) for an unseen language, a language that is not part of the development. Finally, we examine multilingual learning for unsupervised morphological segmentation in low-resource setups. For unsupervised POS tagging, two cross-lingual approaches have been widely adapted: 1) annotation projection, where POS annotations are projected across an aligned parallel text from a source language for which a POS tagger is accessible to the target one prior to training a POS model; and 2) zero-shot model transfer, where a model of a source language is directly applied on texts in the target language. We propose an end-to-end architecture for unsupervised cross-lingual POS tagging via annotation projection in truly low-resource scenarios that do not assume access to parallel corpora that are large in size or represent a specific domain. We integrate and expand the best practices in alignment and projection and design a rich neural architecture that exploits non-contextualized and transformer-based contextualized word embeddings, affix embeddings and word-cluster embeddings. Additionally, since parallel data might be available between the target language and multiple source ones, as in the case of the Bible, we propose different approaches for learning from multiple sources. Finally, we combine our work on unsupervised morphological segmentation and unsupervised cross-lingual POS tagging by conducting unsupervised stem-based cross-lingual POS tagging via annotation projection, which relies on the stem as the core unit of abstraction for alignment and projection, which is beneficial to low-resource morphologically complex languages. We also examine morpheme-based alignment and projection, the use of linguistic priors towards better POS models and the use of segmentation information as learning features in the neural architecture. We conduct comprehensive evaluation and analysis to assess the performance of our approaches of unsupervised morphological segmentation and unsupervised POS tagging and show that they achieve the state-of-the-art performance for the two morphology tasks when evaluated on a large set of languages of different typologies: analytic, fusional, agglutinative and synthetic/polysynthetic.

Thesis (PhD)--Stellenbosch University, 2014. / ENGLISH ABSTRACT: A sign language tutoring system capable of generating detailed context-sensitive feedback to the user is presented in this dissertation. This stands in contrast with existing sign language tutor systems, which lack the capability of providing such feedback. A domain specific language is used to describe the constraints placed on the user’s movements during the course of a sign, allowing complex constraints to be built through the combination of simpler constraints. This same linguistic description is then used to evaluate the user’s movements, and to generate corrective natural language feedback. The feedback is dynamically tailored to the user’s attempt, and automatically targets that correction which would require the least effort on the part of the user. Furthermore, a procedure is introduced which allows feedback to take the form of a simple to-do list, despite the potential complexity of the logical constraints describing the sign. The system is demonstrated using real video sequences of South African Sign Language signs, exploring the different kinds of advice the system can produce, as well as the accuracy of the comments produced. To provide input for the tutor system, the user wears a pair of coloured gloves, and a video of their attempt is recorded. A vision-based hand pose estimation system is proposed which uses the Earth Mover’s Distance to obtain hand pose estimates from images of the user’s hands. A two-tier search strategy is employed, first obtaining nearest neighbours using a simple, but related, metric. It is demonstrated that the two-tier system’s accuracy approaches that of a global search using only the Earth Mover’s Distance, yet requires only a fraction of the time. The system is shown to outperform a closely related system on a set of 500 real images of gloved hands. / AFRIKAANSE OPSOMMING: ’n Gebaretaaltutorstelsel met die vermo¨e om konteks-sensitiewe terugvoer te lewer aan die gebruiker word uiteengesit in hierdie proefskrif. Hierdie staan in kontras met bestaande tutorstelsels, wat nie hierdie kan bied vir die gebruiker nie. ’n Domein-spesifieke taal word gebruik om beperkinge te definieer op die gebruiker se bewegings deur die loop van ’n gebaar. Komplekse beperkinge kan opgebou word uit eenvoudiger beperkinge. Dieselfde linguistieke beskrywing van die gebaar word gebruik om die gebruiker se bewegings te evalueer, en om korrektiewe terugvoer te genereer in teksvorm. Die terugvoer word dinamies aangepas met betrekking tot die gebruiker se probeerslag, en bepaal outomaties die maklikste manier wat die gebruiker sy/haar fout kan korrigeer. ’n Prosedure word uiteengesit om die terugvoer in ’n eenvoudige lysvorm aan te bied, ongeag die kompleksiteit van die linguistieke beskrywing van die gebaar. Die stelsel word gedemonstreer aan die hand van opnames van gebare uit Suid-Afrikaanse Gebaretaal. Die verskeie tipes terugvoer wat die stelsel kan lewer, asook die akkuraatheid van hierdie terugvoer, word ondersoek. Om vir die tutorstelsel intree te bied, dra die gebruiker ’n stel gekleurde handskoene. ’n Visie-gebaseerde handvormafskattingstelsel wat gebruik maak van die Aardverskuiwersafstand (Earth Mover’s Distance) word voorgestel. ’n Twee-vlak soekstrategie word gebruik. ’n Rowwe afstandsmate word gebruik om ’n stel voorlopige handpostuurkandidate te verkry, waarna die stel verfyn word deur gebruik van die Aardverskuiwersafstand. Dit word gewys dat hierdie benaderde strategie se akkuraatheid grens aan die van eksakte soektogte, maar neem slegs ’n fraksie van die tyd. Toetsing op ’n stel van 500 re¨ele beelde, wys dat hierdie stelsel beter presteer as ’n naverwante stelsel uit die literatuur.

The field of guided projectile research has continually grown over the past several decades. Guided projectiles, typically encompassing bullets, mortars, and artillery shells, incorporate some sort of guidance and control mechanism to generate trajectory alterations. This serves to increase accuracy and decrease collateral damage. Control mechanisms for smart weapons must be able to withstand extreme acceleration loads at launch while remain simple for cost and reliability reasons. One type of control mechanism utilizes controllable internal translating masses (ITM's) that oscillate within the projectile to generate control forces. Several techniques for using internal translating masses for smart weapon flight control purposes are explored here. Specifically, the use of ITM's as direct control mechanisms, as a means to increase control authority, and as a means to protect the smart weapons sensor suite are examined. It is first shown that oscillating a mass orthogonal to the projectile axis of symmetry generates reasonable control force in statically-stable rounds. Trade studies examine the impact of mass size, mass offset from the center of gravity, and reductions in static stability on control authority. Then, the topic of static margin control through mass center modification is explored. This is accomplished by translating a mass in flight along the projectile axis of symmetry. Results show that this system allows for greater control authority and reduced throw-off error at launch. Another study, aimed at examining shock reduction potential at launch rather than static margin alteration, also considers ITM movement along the projectile centerline. In these studies, the ITM is comprised of sensitive electronic sensors, and is configured as a first-order damper during launch. Trade study results show that although the mechanism cannot substantially reduce the magnitude of launch loads, it is successful at dampening harmful structural vibrations typically experienced after muzzle exit. Finally, an active control system is developed for the ITM control mechanism using sliding mode methodology. Example cases and Monte Carlo simulations incorporating model uncertainties and sensor errors show that ITM control of projectiles can substantially reduce dispersion error. Furthermore, the novel sliding mode control law is shown to be highly robust to feedback disturbances. In a final study, combined ITM-canard control of projectiles is explored, concluding that ITM mechanisms can serve as a useful supplement in increasing the efficiency of currently-deployed control mechanisms.

We present a multifaceted investigation into the relevance of word order in machine translation. We introduce two tools, DTED and DERP, each using dependency structure to detect differences between the structures of machine-produced translations and human-produced references. DTED applies the principle of Tree Edit Distance to calculate edit operations required to convert one structure into another. Four variants of DTED have been produced, differing in the importance they place on words which match between the two sentences. DERP represents a more detailed procedure, making use of the dependency relations between words when evaluating the disparities between paths connecting matching nodes. In order to empirically evaluate DTED and DERP, and as a standalone contribution, we have produced WOJ-DB, a database of human judgments. Containing scores relating to translation adequacy and more specifically to word order quality, this is intended to support investigations into a wide range of translation phenomena. We report an internal evaluation of the information in WOJ-DB, then use it to evaluate variants of DTED and DERP, both to determine their relative merit and their strength relative to third-party baselines. We present our conclusions about the importance of structure to the tools and their relevance to word order specifically, then propose further related avenues of research suggested or enabled by our work.

This research investigated the feasibility of South African translations of Dewey Decimal Classification (DDC). The study provides an introductory overview of DDC throughout the world, followed by its use in South Africa. The introduction highlights shortcomings and possible solutions – of which translations seem to be the most ideal. This research involved a critical analysis of the literature on DDC translations, a documentary analysis and technology-based research in the form of Google translations and evaluation of parts of Abridged Edition 15 of DDC. The critical analysis of the literature and the documentary analysis identified problems relating to translations, how translations deal with shortcomings in DDC, the fact that no literature exists on multilingual translations, and the process of translations (including the fact that this is an expensive endeavour). It also revealed information about sponsorship and the mixed translation model. The technology-based research, using Google Translate for translations of parts of Abridged Edition 15 and the subsequent evaluation of these translations indicated that Google translations were comprehensive and needed minimum editorial effort. Further to this it paved the way for describing a possible workflow for South African translations and indicated that the parts already translated as well as further Google translations can expedite the translation process. A model for South African translations, based on only the cost of the Pansoft translation software was proposed. The mixed model approach, where some languages are used as main languages (schedules, Relative Index terms and the like) and others for Relative Index terms only, was deemed the most appropriate in the South African context. This led to the conclusion that DDC translations into ten of the official South African languages are indeed feasible. The research supports translations that keep the integrity of DDC intact, with possible expansions based on literary arrant. It is important, though, to get the support of the South African library community and authoritative bodies such as the National Library of South Africa and/or the Library and Information Association of South Africa (LIASA) to negotiate and sign a contract for these translations. / Information Science / D. Litt. et Phil. (Information Science)

The integration of Information and Communication Technology in the indigenous language classroom lags behind compared to other subjects. In many ways, indigenous language teachers find it difficult and to some extent, impossible to integrate ICT into their classroom activities. The focus of this study is to explore the ways in which ICT could be used as a learning tool in an Oshikwanyama First Language classroom. I investigated the use of Wikipedia translation as an additional teaching and learning tool. I concentrated on the impact that ICT tools have on learning, and the motivation it has on learners to learn Oshikwanyama. This qualitative case study was conducted in an urban school in northern Namibia. The adoption of ICT at the school is good as there is a full-fledged computer lab with unlimited wireless internet access. This was a requirement for the project to enable the participants to work online. I purposefully chose higher-level learners (Secondary phase) for this study. I conducted a survey with them on their access to and use of ICT devices in their daily lives, and thereafter conducted a basic computer workshop and a Wikipedia translation project with them. My research findings show that although the use of ICT is part of the learners’ lives, most of the communication through ICT devices is done in English not Oshikwanyama. Wikipedia translation offers a stimulating learning platform for learners to learn Oshikwanyama and English at the same time and this improved their performance in both languages. Furthermore, the Wikipedia translation, which was done collaboratively, gave learners the confidence to work with other learners to create knowledge. Lastly, Wikipedia translation motivates learners to learn Oshikwanyama and use it in their daily ICT interaction.