Link discovery for Chinese/English cross-language web information retrieval

Nowadays people heavily rely on the Internet for information and knowledge. Wikipedia is an online multilingual encyclopaedia that contains a very large number of detailed articles covering most written languages. It is often considered to be a treasury of human knowledge. It includes extensive hypertext links between documents of the same language for easy navigation. However, the pages in different languages are rarely cross-linked except for direct equivalent pages on the same subject in different languages. This could pose serious difficulties to users seeking information or knowledge from different lingual sources, or where there is no equivalent page in one language or another. In this thesis, a new information retrieval task—cross-lingual link discovery (CLLD) is proposed to tackle the problem of the lack of cross-lingual anchored links in a knowledge base such as Wikipedia. In contrast to traditional information retrieval tasks, cross language link discovery algorithms actively recommend a set of meaningful anchors in a source document and establish links to documents in an alternative language. In other words, cross-lingual link discovery is a way of automatically finding hypertext links between documents in different languages, which is particularly helpful for knowledge discovery in different language domains. This study is specifically focused on Chinese / English link discovery (C/ELD). Chinese / English link discovery is a special case of cross-lingual link discovery task. It involves tasks including natural language processing (NLP), cross-lingual information retrieval (CLIR) and cross-lingual link discovery. To justify the effectiveness of CLLD, a standard evaluation framework is also proposed. The evaluation framework includes topics, document collections, a gold standard dataset, evaluation metrics, and toolkits for run pooling, link assessment and system evaluation. With the evaluation framework, performance of CLLD approaches and systems can be quantified. This thesis contributes to the research on natural language processing and cross-lingual information retrieval in CLLD: 1) a new simple, but effective Chinese segmentation method, n-gram mutual information, is presented for determining the boundaries of Chinese text; 2) a voting mechanism of name entity translation is demonstrated for achieving a high precision of English / Chinese machine translation; 3) a link mining approach that mines the existing link structure for anchor probabilities achieves encouraging results in suggesting cross-lingual Chinese / English links in Wikipedia. This approach was examined in the experiments for better, automatic generation of cross-lingual links that were carried out as part of the study. The overall major contribution of this thesis is the provision of a standard evaluation framework for cross-lingual link discovery research. It is important in CLLD evaluation to have this framework which helps in benchmarking the performance of various CLLD systems and in identifying good CLLD realisation approaches. The evaluation methods and the evaluation framework described in this thesis have been utilised to quantify the system performance in the NTCIR-9 Crosslink task which is the first information retrieval track of this kind.

An evaluation of corpus-driven measures of medical concept similarity for information retrieval

Measures of semantic similarity between medical concepts are central to a number of techniques in medical informatics, including query expansion in medical information retrieval. Previous work has mainly considered thesaurus-based path measures of semantic similarity and has not compared different corpus-driven approaches in depth. We evaluate the effectiveness of eight common corpus-driven measures in capturing semantic relatedness and compare these against human judged concept pairs assessed by medical professionals. Our results show that certain corpus-driven measures correlate strongly (approx 0.8) with human judgements. An important finding is that performance was significantly affected by the choice of corpus used in priming the measure, i.e., used as evidence from which corpus-driven similarities are drawn. This paper provides guidelines for the implementation of semantic similarity measures for medical informatics and concludes with implications for medical information retrieval.

A tensor encoding model of word meaning : theory and application to information retrieval

This project was a step forward in developing and evaluating a novel, mathematical model that can deduce the meaning of words based on their use in language. This model can be applied to a wide range of natural language applications, including the information seeking process most of us undertake on a daily basis.

Postgraduate response to an information retrieval credit course

Information skills instruction for research candidates bas recently been formalised as coursework at the Queensland University of Technology. Feedback solicited from participants suggests that students benefit from such coursework in a number of ways. Their perception of the value of specific content areas to their literature review and thesis presentation is favourable. A small group of students who participated in Interviews identified five ways in which the coursework assisted the research process. As Instructors continue to work with the post·graduate community it would be useful to deepen our understanding of how such instruction is perceived and the benefits which can be derived from it.

Secured e-health data retrieval in DaaS and Big Data

Big Data is a rising IT trend similar to cloud computing, social networking or ubiquitous computing. Big Data can offer beneficial scenarios in the e-health arena. However, one of the scenarios can be that Big Data needs to be kept secured for a long period of time in order to gain its benefits such as finding cures for infectious diseases and protecting patient privacy. From this connection, it is beneficial to analyse Big Data to make meaningful information while the data is stored securely. Therefore, the analysis of various database encryption techniques is essential. In this study, we simulated 3 types of technical environments, namely, Plain-text, Microsoft Built-in Encryption, and custom Advanced Encryption Standard, using Bucket Index in Data-as-a-Service. The results showed that custom AES-DaaS has a faster range query response time than MS built-in encryption. Furthermore, while carrying out the scalability test, we acknowledged that there are performance thresholds depending on physical IT resources. Therefore, for the purpose of efficient Big Data management in eHealth it is noteworthy to examine their scalability limits as well even if it is under a cloud computing environment. In addition, when designing an e-health database, both patient privacy and system performance needs to be dealt as top priorities.

Towards the retrieval of accurate OD matrices from Bluetooth data : lessons learned from 2 years of data

The Bluetooth technology is being increasingly used to track vehicles throughout their trips, within urban networks and across freeway stretches. One important opportunity offered by this type of data is the measurement of Origin-Destination patterns, emerging from the aggregation and clustering of individual trips. In order to obtain accurate estimations, however, a number of issues need to be addressed, through data filtering and correction techniques. These issues mainly stem from the use of the Bluetooth technology amongst drivers, and the physical properties of the Bluetooth sensors themselves. First, not all cars are equipped with discoverable Bluetooth devices and the Bluetooth-enabled vehicles may belong to some small socio-economic groups of users. Second, the Bluetooth datasets include data from various transport modes; such as pedestrian, bicycles, cars, taxi driver, buses and trains. Third, the Bluetooth sensors may fail to detect all of the nearby Bluetooth-enabled vehicles. As a consequence, the exact journey for some vehicles may become a latent pattern that will need to be extracted from the data. Finally, sensors that are in close proximity to each other may have overlapping detection areas, thus making the task of retrieving the correct travelled path even more challenging. The aim of this paper is twofold. We first give a comprehensive overview of the aforementioned issues. Further, we propose a methodology that can be followed, in order to cleanse, correct and aggregate Bluetooth data. We postulate that the methods introduced by this paper are the first crucial steps that need to be followed in order to compute accurate Origin-Destination matrices in urban road networks.

Retrieval of health advice on the web: AEHRC at ShARe/CLEF eHealth Evaluation Lab Task 3

This paper details the participation of the Australian e- Health Research Centre (AEHRC) in the ShARe/CLEF 2013 eHealth Evaluation Lab { Task 3. This task aims to evaluate the use of information retrieval (IR) systems to aid consumers (e.g. patients and their relatives) in seeking health advice on the Web. Our submissions to the ShARe/CLEF challenge are based on language models generated from the web corpus provided by the organisers. Our baseline system is a standard Dirichlet smoothed language model. We enhance the baseline by identifying and correcting spelling mistakes in queries, as well as expanding acronyms using AEHRC's Medtex medical text analysis platform. We then consider the readability and the authoritativeness of web pages to further enhance the quality of the document ranking. Measures of readability are integrated in the language models used for retrieval via prior probabilities. Prior probabilities are also used to encode authoritativeness information derived from a list of top-100 consumer health websites. Empirical results show that correcting spelling mistakes and expanding acronyms found in queries signi cantly improves the e ectiveness of the language model baseline. Readability priors seem to increase retrieval e ectiveness for graded relevance at early ranks (nDCG@5, but not precision), but no improvements are found at later ranks and when considering binary relevance. The authoritativeness prior does not appear to provide retrieval gains over the baseline: this is likely to be because of the small overlap between websites in the corpus and those in the top-100 consumer-health websites we acquired.

A concept-based retrieval method for entity-oriented search

Entity-oriented retrieval aims to return a list of relevant entities rather than documents to provide exact answers for user queries. The nature of entity-oriented retrieval requires identifying the semantic intent of user queries, i.e., understanding the semantic role of query terms and determining the semantic categories which indicate the class of target entities. Existing methods are not able to exploit the semantic intent by capturing the semantic relationship between terms in a query and in a document that contains entity related information. To improve the understanding of the semantic intent of user queries, we propose concept-based retrieval method that not only automatically identifies the semantic intent of user queries, i.e., Intent Type and Intent Modifier but introduces concepts represented by Wikipedia articles to user queries. We evaluate our proposed method on entity profile documents annotated by concepts from Wikipedia category and list structure. Empirical analysis reveals that the proposed method outperforms several state-of-the-art approaches.

Indexing and efficient instance-based retrieval of process models using untanglings

Process-Aware Information Systems (PAISs) support executions of operational processes that involve people, resources, and software applications on the basis of process models. Process models describe vast, often infinite, amounts of process instances, i.e., workflows supported by the systems. With the increasing adoption of PAISs, large process model repositories emerged in companies and public organizations. These repositories constitute significant information resources. Accurate and efficient retrieval of process models and/or process instances from such repositories is interesting for multiple reasons, e.g., searching for similar models/instances, filtering, reuse, standardization, process compliance checking, verification of formal properties, etc. This paper proposes a technique for indexing process models that relies on their alternative representations, called untanglings. We show the use of untanglings for retrieval of process models based on process instances that they specify via a solution to the total executability problem. Experiments with industrial process models testify that the proposed retrieval approach is up to three orders of magnitude faster than the state of the art.

Efficient top-k retrieval with signatures

This paper describes a new method of indexing and searching large binary signature collections to efficiently find similar signatures, addressing the scalability problem in signature search. Signatures offer efficient computation with acceptable measure of similarity in numerous applications. However, performing a complete search with a given search argument (a signature) requires a Hamming distance calculation against every signature in the collection. This quickly becomes excessive when dealing with large collections, presenting issues of scalability that limit their applicability. Our method efficiently finds similar signatures in very large collections, trading memory use and precision for greatly improved search speed. Experimental results demonstrate that our approach is capable of finding a set of nearest signatures to a given search argument with a high degree of speed and fidelity.

A dedicated retrieval and transfer service : the QUARTS project

Background The transfer and/or retrieval of a critically patient is inherently dangerous not only for the patient but for staff as well. The quality and experience of unplanned transfers can influence patient mortality and morbidity. However, international evidence suggests that dedicated transfer/retrieval teams can improve mortality and morbidity outcomes. Aims The initial aim of this paper is to describe an in-house competency-based training programme, which encompasses the STaR approach to develop members of our existing nursing team to be part of the dedicated transfer/retrieval service. The paper also presents audit data findings which examined the source of referrals, number of patients actually transferred and clinical status of those being transferred. Results Audit data illustrate that the most frequent source of referrals comes from Accident and Emergency and the Surgical Directorate with the most common presenting condition being cardio-respiratory failure or arrest. Audit data reveal that the number of patients actually transferred or retrieved is relatively small (33%) compared with the overall number of requests for assistance. However, 36% of those patients transferred had a level 2 or level 3 acuity status that necessitated the admission to a critical care area. Conclusions A number of studies have concluded that the ill-experienced and ill-equipped transfer team can place patients’ at serious risk of harm. Whether planned or unplanned, dedicated critical care transfer/retrieval teams have been shown to reduce patient mortality and morbidity.

Hidden credential retrieval from a reusable password

We revisit the venerable question of access credentials management, which concerns the techniques that we, humans with limited memory, must employ to safeguard our various access keys and tokens in a connected world. Although many existing solutions can be employed to protect a long secret using a short password, those solutions typically require certain assumptions on the distribution of the secret and/or the password, and are helpful against only a subset of the possible attackers. After briefly reviewing a variety of approaches, we propose a user-centric comprehensive model to capture the possible threats posed by online and offline attackers, from the outside and the inside, against the security of both the plaintext and the password. We then propose a few very simple protocols, adapted from the Ford-Kaliski server-assisted password generator and the Boldyreva unique blind signature in particular, that provide the best protection against all kinds of threats, for all distributions of secrets. We also quantify the concrete security of our approach in terms of online and offline password guesses made by outsiders and insiders, in the random-oracle model. The main contribution of this paper lies not in the technical novelty of the proposed solution, but in the identification of the problem and its model. Our results have an immediate and practical application for the real world: they show how to implement single-sign-on stateless roaming authentication for the internet, in a ad-hoc user-driven fashion that requires no change to protocols or infrastructure.

A formalization of logical imaging for information retrieval using quantum theory

In this paper we introduce a formalization of Logical Imaging applied to IR in terms of Quantum Theory through the use of an analogy between states of a quantum system and terms in text documents. Our formalization relies upon the Schrodinger Picture, creating an analogy between the dynamics of a physical system and the kinematics of probabilities generated by Logical Imaging. By using Quantum Theory, it is possible to model more precisely contextual information in a seamless and principled fashion within the Logical Imaging process. While further work is needed to empirically validate this, the foundations for doing so are provided.

Estimating interference in the QPRP for subtopic retrieval

The Quantum Probability Ranking Principle (QPRP) has been recently proposed, and accounts for interdependent document relevance when ranking. However, to be instantiated, the QPRP requires a method to approximate the interference" between two documents. In this poster, we empirically evaluate a number of different methods of approximation on two TREC test collections for subtopic retrieval. It is shown that these approximations can lead to significantly better retrieval performance over the state of the art.

Revisiting logical imaging for information retrieval

Retrieval with Logical Imaging is derived from belief revision and provides a novel mechanism for estimating the relevance of a document through logical implication (i.e. P(q -> d)). In this poster, we perform the first comprehensive evaluation of Logical Imaging (LI) in Information Retrieval (IR) across several TREC test Collections. When compared against standard baseline models, we show that LI fails to improve performance. This failure can be attributed to a nuance within the model that means non-relevant documents are promoted in the ranking, while relevant documents are demoted. This is an important contribution because it not only contextualizes the effectiveness of LI, but crucially ex- plains why it fails. By addressing this nuance, future LI models could be significantly improved.