Building instance knowledge network for word sense disambiguation

In this paper, a new high precision focused word sense disambiguation (WSD) approach is proposed, which not only attempts to identify the proper sense for a word but also provides the probabilistic evaluation for the identification confidence at the same time. A novel Instance Knowledge Network (IKN) is built to generate and maintain semantic knowledge at the word, type synonym set and instance levels. Related algorithms based on graph matching are developed to train IKN with probabilistic knowledge and to use IKN for probabilistic word sense disambiguation. Based on the Senseval-3 all-words task, we run extensive experiments to show the performance enhancements in different precision ranges and the rationality of probabilistic based automatic confidence evaluation of disambiguation. We combine our WSD algorithm with five best WSD algorithms in senseval-3 all words tasks. The results show that the combined algorithms all outperform the corresponding algorithms.

Inducing shades of meaning by matrix methods : a first step towards thematic analysis of opinion

This article explores two matrix methods to induce the ``shades of meaning" (SoM) of a word. A matrix representation of a word is computed from a corpus of traces based on the given word. Non-negative Matrix Factorisation (NMF) and Singular Value Decomposition (SVD) compute a set of vectors corresponding to a potential shade of meaning. The two methods were evaluated based on loss of conditional entropy with respect to two sets of manually tagged data. One set reflects concepts generally appearing in text, and the second set comprises words used for investigations into word sense disambiguation. Results show that for NMF consistently outperforms SVD for inducing both SoM of general concepts as well as word senses. The problem of inducing the shades of meaning of a word is more subtle than that of word sense induction and hence relevant to thematic analysis of opinion where nuances of opinion can arise.

Calculating shades of meaning in semantic spaces

This thesis introduces the problem of conceptual ambiguity, or Shades of Meaning (SoM) that can exist around a term or entity. As an example consider President Ronald Reagan the ex-president of the USA, there are many aspects to him that are captured in text; the Russian missile deal, the Iran-contra deal and others. Simply finding documents with the word “Reagan” in them is going to return results that cover many different shades of meaning related to "Reagan". Instead it may be desirable to retrieve results around a specific shade of meaning of "Reagan", e.g., all documents relating to the Iran-contra scandal. This thesis investigates computational methods for identifying shades of meaning around a word, or concept. This problem is related to word sense ambiguity, but is more subtle and based less on the particular syntactic structures associated with or around an instance of the term and more with the semantic contexts around it. A particularly noteworthy difference from typical word sense disambiguation is that shades of a concept are not known in advance. It is up to the algorithm itself to ascertain these subtleties. It is the key hypothesis of this thesis that reducing the number of dimensions in the representation of concepts is a key part of reducing sparseness and thus also crucial in discovering their SoMwithin a given corpus.

Multilingual lexical resources to detect cognates in non-aligned texts

The identification of cognates between two distinct languages has recently start- ed to attract the attention of NLP re- search, but there has been little research into using semantic evidence to detect cognates. The approach presented in this paper aims to detect English-French cog- nates within monolingual texts (texts that are not accompanied by aligned translat- ed equivalents), by integrating word shape similarity approaches with word sense disambiguation techniques in order to account for context. Our implementa- tion is based on BabelNet, a semantic network that incorporates a multilingual encyclopedic dictionary. Our approach is evaluated on two manually annotated da- tasets. The first one shows that across different types of natural text, our method can identify the cognates with an overall accuracy of 80%. The second one, con- sisting of control sentences with semi- cognates acting as either true cognates or false friends, shows that our method can identify 80% of semi-cognates acting as cognates but also identifies 75% of the semi-cognates acting as false friends.

Predicting sense convergence with distributional semantics : an application to the CogALex-IV 2014 shared task

This paper presents our system to address the CogALex-IV 2014 shared task of identifying a single word most semantically related to a group of 5 words (queries). Our system uses an implementation of a neural language model and identifies the answer word by finding the most semantically similar word representation to the sum of the query representations. It is a fully unsupervised system which learns on around 20% of the UkWaC corpus. It correctly identifies 85 exact correct targets out of 2,000 queries, 285 approximate targets in lists of 5 suggestions.

Making sense of an everyday science text : linguistic, visual and spatial design

In this article, we take a close look at the literacy demands of one task from the ‘Marvellous Micro-organisms Stage 3 Life and Living’ Primary Connections unit (Australian Academy of Science, 2005). One lesson from the unit, ‘Exploring Bread’, (pp 4-8) asks students to ‘use bread labels to locate ingredient information and synthesise understanding of bread ingredients’. We draw upon a framework offered by the New London Group (2000), that of linguistic, visual and spatial design, to consider in more detail three bread wrappers and from there the complex literacies that students need to interrelate to undertake the required task. Our findings are that although bread wrappers are an example of an everyday science text, their linguistic, visual and spatial designs and their interrelationship are not trivial. We conclude by reinforcing the need for teachers of science to also consider how the complex design elements of everyday science texts and their interrelated literacies are made visible through instructional practice.

At-the-edge-of-the-forest

This exhibition was the outcome of a personal arts-based exploration of the meaning of interiority. Through the process it was found that existentially the architectural wall differentiating inside from outside does not exist but operates as a space of overlap, a groundless ground providing for dwelling in the real existential sense of the word.

Social justice and high-quality human services : visioning the place of a contemporary professional association

The current world situation is plagued by “wicked problems” and a widespread sense of “things are going to get worse”. We confront the almost imponderable consequences of global habitat destruction and climate change, as well as the meltdown of the financial markets with their largely yet to be seen damage to the “real economy”. These things will have considerable negative impacts on the social system and people's lives, particularly the disadvantaged and socially excluded, and require innovative policy and program responses delivered by caring, intelligent, and committed practitioners. These gargantuan issues put into perspective the difficulties that confront social, welfare, and community work today. Yet, in times of trouble, social work and human services tend to do well. For example, although Australian Social Workers and Welfare and Community Workers have experienced phenomenal job growth over the past 5 years, they also have good prospects for future growth and above average salaries in the seventh and sixth deciles, respectively (Department of Education, Employment and Workplace Relations, 2008). I aim to examine the host of reasons why the pursuit of social justice and high-quality human services is difficult to attain in today's world and then consider how the broadly defined profession of social welfare practitioners may collectively take action to (a) respond in ways that reassert our role in compassionately assisting the downtrodden and (b) reclaim the capacity to be a significant body of professional expertise driving social policy and programs. For too long social work has responded to the wider factors it confronts through a combination of ignoring them, critiquing from a distance, and concentrating on the job at hand and our day-to-day responsibilities. Unfortunately, “holding the line” has proved futile and, little by little, the broad social mandate and role of social welfare has altered until, currently, most social programs entail significant social surveillance of troublesome or dangerous groups, rather than assistance. At times it almost seems like the word “help” has been lost in the political and managerial lexicon, replaced by “manage” and “control”. Our values, beliefs, and ethics are under real threat as guiding principles for social programs.

Look before you leap : the epistemic violence that sometimes hides behind the word "inclusion"

This paper demonstrates how Indigenous Studies is controlled in some Australian universities in ways that continue the marginalisation, denigration and exploitation of Indigenous peoples. Moreover, it shows how the engagement of white notions of “inclusion” can result in the maintenance of racism, systemic marginalisation, white race privilege and radicalised subjectivity. A case study will be utilised which draws from the experience of two Indigenous scholars who were invited to be part of a panel to review one Australian university’s plan and courses in Indigenous studies. The case study offers the opportunity to destabilise the relationships between oppression and privilege and the epistemology that maintains them. The paper argues for the need to examine exactly what is being offered when universities provide opportunities for “inclusion”.

Making sense of working lives and working choices : the role of satirical cartoons

This study examined the tone and content of 107 political, satirical cartoons images published in the popular culture forum of mainstream newspapers. The cartoons illustrated the reform of the industrial relations system in Australia in 2005 and 2006. The images were conveyed in a moderate tone. That is, they were more about poking fun at and questioning authority and power, rather than simply describing the issues on one hand, or demonstrating any revolutionary fervor on the other. The cartoons’ content represented many of the concerns and issues being voiced by employer groups, government, opposition, unions and the media at the time. Themes likely to evoke a strong response from the readership included the importance of a collective response in voicing opposition to the legislation and enacting change, the risks to fundamental working conditions, the stealth and dogma associated with the rollout of the changes and the increasing disparity in wealth and power between employers and workers. The images were an important part of the wider discourse and a mechanism which helped place industrial relations squarely in the minds of working Australians.

Sense and sensibility by Jane Austen

It's the fact that it's Austen mentioned here that provokes a response. The broad cultural veneration of Jane Austen means that even those who have never read her work are likely to have a strong reaction to Emerson's famou quotation. It is worth considering Emerson's accustion befor teaching an Austen novel, as many of his assertions will be amde - albeit in different terms - byt twenty-first-century students.

Making sense of the resource-based view?

The Resource Based View (RBV) of strategic management has been criticized for relying on inconsistent assumptions of rationality, and mutually inconsistent underlying hypotheses. In this paper, I outline how these critiques can be addressed by re-building RBV on a sense-making foundation. The core notions from sense-making of bounded cognition, retrospective sense-making, incrementalism, loose coupling, causal maps and organizational paradigm are introduced. These are then used to propose a re-construction of key RBV constructs, extending some conceptual discussions, and providing for a conceptually consistent formulation. Implications for the use of RBV as a theory and future research are discussed.

Word Segmentation for Chinese Wikipedia Using N-Gram Mutual Information

In this paper, we propose an unsupervised segmentation approach, named "n-gram mutual information", or NGMI, which is used to segment Chinese documents into n-character words or phrases, using language statistics drawn from the Chinese Wikipedia corpus. The approach alleviates the tremendous effort that is required in preparing and maintaining the manually segmented Chinese text for training purposes, and manually maintaining ever expanding lexicons. Previously, mutual information was used to achieve automated segmentation into 2-character words. The NGMI approach extends the approach to handle longer n-character words. Experiments with heterogeneous documents from the Chinese Wikipedia collection show good results.

Word-perfect Gatsby overcomes its flaws

Review of 'Gatz', Elevator Repair Company / Brisbane Powerhouse, published in The Australian, 12 May 2009.