Exploring automatic feature selection for transition-based dependency parsing

En este artículo se investigan técnicas automáticas para encontrar un modelo óptimo de características en el caso de un analizador de dependencias basado en transiciones. Mostramos un estudio comparativo entre algoritmos de búsqueda, sistemas de validación y reglas de decisión demostrando al mismo tiempo que usando nuestros métodos es posible conseguir modelos complejos que proporcionan mejores resultados que los modelos que siguen configuraciones por defecto.

From constituents to syntax-oriented dependencies

This paper describes the automatic process of building a dependency annotated corpus based on Ancora constituent structures. The Ancora corpus already has a dependency structure information layer, but the new annotated data applies a purely syntactic orientation and offers in this way a new resource to the linguistic research community. The paper details the process of reannotating the corpus, the linguistic criteria used and the obtained results.

From Aari to Zulu: Massively Multilingual Creation of Language Tools using Interlinear Glossed Text

Thesis (Ph.D.)--University of Washington, 2016-08

SEQUENTIAL DECISIONS AND PREDICTIONS IN NATURAL LANGUAGE PROCESSING

Natural language processing has achieved great success in a wide range of ap- plications, producing both commercial language services and open-source language tools. However, most methods take a static or batch approach, assuming that the model has all information it needs and makes a one-time prediction. In this disser- tation, we study dynamic problems where the input comes in a sequence instead of all at once, and the output must be produced while the input is arriving. In these problems, predictions are often made based only on partial information. We see this dynamic setting in many real-time, interactive applications. These problems usually involve a trade-off between the amount of input received (cost) and the quality of the output prediction (accuracy). Therefore, the evaluation considers both objectives (e.g., plotting a Pareto curve). Our goal is to develop a formal understanding of sequential prediction and decision-making problems in natural language processing and to propose efficient solutions. Toward this end, we present meta-algorithms that take an existent batch model and produce a dynamic model to handle sequential inputs and outputs. Webuild our framework upon theories of Markov Decision Process (MDP), which allows learning to trade off competing objectives in a principled way. The main machine learning techniques we use are from imitation learning and reinforcement learning, and we advance current techniques to tackle problems arising in our settings. We evaluate our algorithm on a variety of applications, including dependency parsing, machine translation, and question answering. We show that our approach achieves a better cost-accuracy trade-off than the batch approach and heuristic-based decision- making approaches. We first propose a general framework for cost-sensitive prediction, where dif- ferent parts of the input come at different costs. We formulate a decision-making process that selects pieces of the input sequentially, and the selection is adaptive to each instance. Our approach is evaluated on both standard classification tasks and a structured prediction task (dependency parsing). We show that it achieves similar prediction quality to methods that use all input, while inducing a much smaller cost. Next, we extend the framework to problems where the input is revealed incremen- tally in a fixed order. We study two applications: simultaneous machine translation and quiz bowl (incremental text classification). We discuss challenges in this set- ting and show that adding domain knowledge eases the decision-making problem. A central theme throughout the chapters is an MDP formulation of a challenging problem with sequential input/output and trade-off decisions, accompanied by a learning algorithm that solves the MDP.

Parsing Arabic relative clauses: A paninian dependency grammar approach

We present an approach to parsing rehive clauses in Arabic in the tradition of the Paninian Grammar Frumework/2] which leads to deriving U common logicul form for equivalent sentences. Particular attention is paid to the analysis of resumptive pronouns in the retrieval of syntuctico-semantic relationships. The analysis arises from the development of a lexicalised dependency grammar for Arabic that has application for machine translation.

Exchange relationships in building services maintenance activity : a test of transaction cost economics and the resource dependency view

The firm is faced with a decision concerning the nature of intra-organizational exchange relationships with internal human resources and the nature or inter-organizational exchange relationships with market firms. In both situations, the firm can develop an exchange that ranges from a discrete exchange to a relational exchange. Transaction Cost Economics (TCE) and the Resource Dependency View (RDV) represent alternative efficiency-based explanations fo the nature of the exchange relationship. The aim of the paper is to test these two theories in respect of air conditioning maintenance in retail centres. Multiple sources of information are genereated from case studies of Australian retail centres to test these theories in respoect of internalized operations management (concerning strategic aspects of air conditioning maintenance) and externalized planned routine air conditioning maintenance. The analysis of the data centres on pattern matching. It is concluded that the data supports TCE - on the basis of a development in TCE's contractual schema. Further research is suggested towards taking a pluralistic stance and developing a combined efficiency and power hypothesis - upon which Williamson has speculated. For practice, the conclusions also offer a timely cautionary note concerning the adoption of one approach in all exchange relationships.

Stigma reported by nurses related to those experiencing drug and alcohol dependency : a phemonenological study

Alcohol and drug dependency is a widespread health and social issue encountered by registered nurses in contemporary practice. A study aiming to describe the experiences of registered nurses working in an alcohol and drug unit in South East Queensland was implemented. Data were analysed via Giorgi’s phenomenological method and an unexpected but significant finding highlighted the frustration felt by registered nurses regarding experiences of stigma they identified in their daily work encounters. Secondary analysis confirmed the phenomenon of stigma with three themes: (1) inappropriate judgement; (2) advocacy; and (3) education. Resultantly, findings concluded registered nurses’ working in this field need to become advocates for their clients, ensuring professional conduct is upheld at all times. This paper recommends that stigma could be addressed by incorporating alcohol and other drug dependency subjects and clinical placements into the curriculum of the Bachelor of Nursing degrees, and in-services for all practising registered nurses.

Transportation behaviours of older adults : an investigation into car dependency in urban Australia

Aim: Increased car dependency amongst Australia's ageing population may result in increased social isolation and other health impacts associated with the cessation of driving. While public transport represents an alternative to car usage, patronage remains low amongst senior cohorts. This study investigates the facilitators and barriers to public transport patronage and the nature of car dependence among older Australians. Method: Data was gathered from a sample of 24 adults (mean = 70.33 years) through a combination of quantitative (remote behavioural observation) and qualitative (interviews) investigation. Results: Findings suggest factors of relative convenience, affordability and health/mobility dictate choices of transport mode. The car is considered more convenient for the majority of suburban trips irrespective of the availability of public transport. Conclusion: Policy attention should focus on providing better education and information regarding driving cessation and addressing aged-specific social aspects of public transport including the accommodation of various health and mobility issues.

Parsing the Australian curriculum English : grammar, multimodality and cross-cultural texts

The release of the Australian Curriculum English (ACE) by the Australian Curriculum, Assessment and Reporting Authority (ACARA) has revived debates about the role of grammar as English content knowledge. We consider some of the discussion circulating in the mainstream media vis-à-vis the intent of the ACE. We conclude that this curriculum draws upon the complementary tenets of traditional Latin-based grammar and systemic functional linguistics across the three strands of Language, Literature and Literacy in innovative ways. We argue that such an approach is necessary for working with contemporary multimodal and cross-cultural texts. To demonstrate the utility of this new approach, we draw out a set of learning outcomes from Year 6 and then map out a framework for relating the outcomes to the form and function of multimodal language. As a case in point, our analysis is of two online Coca-Cola advertising texts, one each from South Korea and Australia.

Time dependency of molecular rate estimates and systematic overestimation of recent divergence times

Studies of molecular evolutionary rates have yielded a wide range of rate estimates for various genes and taxa. Recent studies based on population-level and pedigree data have produced remarkably high estimates of mutation rate, which strongly contrast with substitution rates inferred in phylogenetic (species-level) studies. Using Bayesian analysis with a relaxed-clock model, we estimated rates for three groups of mitochondrial data: avian protein-coding genes, primate protein-coding genes, and primate d-loop sequences. In all three cases, we found a measurable transition between the high, short-term (<1–2 Myr) mutation rate and the low, long-term substitution rate. The relationship between the age of the calibration and the rate of change can be described by a vertically translated exponential decay curve, which may be used for correcting molecular date estimates. The phylogenetic substitution rates in mitochondria are approximately 0.5% per million years for avian protein-coding sequences and 1.5% per million years for primate protein-coding and d-loop sequences. Further analyses showed that purifying selection offers the most convincing explanation for the observed relationship between the estimated rate and the depth of the calibration. We rule out the possibility that it is a spurious result arising from sequence errors, and find it unlikely that the apparent decline in rates over time is caused by mutational saturation. Using a rate curve estimated from the d-loop data, several dates for last common ancestors were calculated: modern humans and Neandertals (354 ka; 222–705 ka), Neandertals (108 ka; 70–156 ka), and modern humans (76 ka; 47–110 ka). If the rate curve for a particular taxonomic group can be accurately estimated, it can be a useful tool for correcting divergence date estimates by taking the rate decay into account. Our results show that it is invalid to extrapolate molecular rates of change across different evolutionary timescales, which has important consequences for studies of populations, domestication, conservation genetics, and human evolution.

Evidence for time dependency of molecular rate estimates

Long-term changes in the genetic composition of a population occur by the fixation of new mutations, a process known as substitution. The rate at which mutations arise in a population and the rate at which they are fixed are expected to be equal under neutral conditions (Kimura, 1968). Between the appearance of a new mutation and its eventual fate of fixation or loss, there will be a period in which it exists as a transient polymorphism in the population (Kimura and Ohta, 1971). If the majority of mutations are deleterious (and nonlethal), the fixation probabilities of these transient polymorphisms are reduced and the mutation rate will exceed the substitution rate (Kimura, 1983). Consequently, different apparent rates may be observed on different time scales of the molecular evolutionary process (Penny, 2005; Penny and Holmes, 2001). The substitution rate of the mitochondrial protein-coding genes of birds and mammals has been traditionally recognized to be about 0.01 substitutions/site/million years (Myr) (Brown et al., 1979; Ho, 2007; Irwin et al., 1991; Shields and Wilson, 1987), with the noncoding D-loop evolving several times more quickly (e.g., Pesole et al., 1992; Quinn, 1992). Over the past decade, there has been mounting evidence that instantaneous mutation rates substantially exceed substitution rates, in a range of organisms (e.g., Denver et al., 2000; Howell et al., 2003; Lambert et al., 2002; Mao et al., 2006; Mumm et al., 1997; Parsons et al., 1997; Santos et al., 2005). The immediate reaction to the first of these findings was that the polymorphisms generated by the elevated mutation rate are short-lived, perhaps extending back only a few hundred years (Gibbons, 1998; Macaulay et al., 1997). That is, purifying selection was thought to remove these polymorphisms very rapidly.

A world map of knowledge in the making : Wikipedia's Inter-Language Linkage as a dependency explorer of global knowledge accumulation

Analysis of Wikipedia's inter-language links provides insight into a new mechanism of knowledge sharing and linking worldwide.