An evaluation framework for cross-lingual link discovery

Cross-Lingual Link Discovery (CLLD) is a new problem in Information Retrieval. The aim is to automatically identify meaningful and relevant hypertext links between documents in different languages. This is particularly helpful in knowledge discovery if a multi-lingual knowledge base is sparse in one language or another, or the topical coverage in each language is different; such is the case with Wikipedia. Techniques for identifying new and topically relevant cross-lingual links are a current topic of interest at NTCIR where the CrossLink task has been running since the 2011 NTCIR-9. This paper presents the evaluation framework for benchmarking algorithms for cross-lingual link discovery evaluated in the context of NTCIR-9. This framework includes topics, document collections, assessments, metrics, and a toolkit for pooling, assessment, and evaluation. The assessments are further divided into two separate sets: manual assessments performed by human assessors; and automatic assessments based on links extracted from Wikipedia itself. Using this framework we show that manual assessment is more robust than automatic assessment in the context of cross-lingual link discovery.

Examination of the properties of IMRT and VMAT beams and evaluation against pre-treatment quality assurance results

This study aimed to provide a detailed evaluation and comparison of a range of modulated beam evaluation metrics, in terms of their correlation with QA testing results and their variation between treatment sites, for a large number of treatments. Ten metrics including the modulation index (MI), fluence map complexity (FMC), modulation complexity score (MCS), mean aperture displacement (MAD) and small aperture score (SAS) were evaluated for 546 beams from 122 IMRT and VMAT treatment plans targeting the anus, rectum, endometrium, brain, head and neck and prostate. The calculated sets of metrics were evaluated in terms of their relationships to each other and their correlation with the results of electronic portal imaging based quality assurance (QA) evaluations of the treatment beams. Evaluation of the MI, MAD and SAS suggested that beams used in treatments of the anus, rectum, head and neck were more complex than the prostate and brain treatment beams. Seven of the ten beam complexity metrics were found to be strongly correlated with the results from QA testing of the IMRT beams (p < 0.00008). For example, Values of SAS (with MLC apertures narrower than 10 mm defined as “small”) less than 0.2 also identified QA passing IMRT beams with 100% specificity. However, few of the metrics are correlated with the results from QA testing of the VMAT beams, whether they were evaluated as whole 360◦ arcs or as 60◦ sub-arcs. Select evaluation of beam complexity metrics (at least MI, MCS and SAS) is therefore recommended, as an intermediate step in the IMRT QA chain. Such evaluation may also be useful as a means of periodically reviewing VMAT planning or optimiser performance.

Comprehensive evaluation of multisatellite precipitation estimates over India using gridded rainfall data

This study presents a comprehensive evaluation of five widely used multisatellite precipitation estimates (MPEs) against 1 degrees x 1 degrees gridded rain gauge data set as ground truth over India. One decade observations are used to assess the performance of various MPEs (Climate Prediction Center (CPC)-South Asia data set, CPC Morphing Technique (CMORPH), Precipitation Estimation From Remotely Sensed Information Using Artificial Neural Networks, Tropical Rainfall Measuring Mission's Multisatellite Precipitation Analysis (TMPA-3B42), and Global Precipitation Climatology Project). All MPEs have high detection skills of rain with larger probability of detection (POD) and smaller ``missing'' values. However, the detection sensitivity differs from one product (and also one region) to the other. While the CMORPH has the lowest sensitivity of detecting rain, CPC shows highest sensitivity and often overdetects rain, as evidenced by large POD and false alarm ratio and small missing values. All MPEs show higher rain sensitivity over eastern India than western India. These differential sensitivities are found to alter the biases in rain amount differently. All MPEs show similar spatial patterns of seasonal rain bias and root-mean-square error, but their spatial variability across India is complex and pronounced. The MPEs overestimate the rainfall over the dry regions (northwest and southeast India) and severely underestimate over mountainous regions (west coast and northeast India), whereas the bias is relatively small over the core monsoon zone. Higher occurrence of virga rain due to subcloud evaporation and possible missing of small-scale convective events by gauges over the dry regions are the main reasons for the observed overestimation of rain by MPEs. The decomposed components of total bias show that the major part of overestimation is due to false precipitation. The severe underestimation of rain along the west coast is attributed to the predominant occurrence of shallow rain and underestimation of moderate to heavy rain by MPEs. The decomposed components suggest that the missed precipitation and hit bias are the leading error sources for the total bias along the west coast. All evaluation metrics are found to be nearly equal in two contrasting monsoon seasons (southwest and northeast), indicating that the performance of MPEs does not change with the season, at least over southeast India. Among various MPEs, the performance of TMPA is found to be better than others, as it reproduced most of the spatial variability exhibited by the reference.

Image, Video and 3D Data Registration: Medical, Satellite and Video Processing Applications with Quality Metrics

Data registration refers to a series of techniques for matching or bringing similar objects or datasets together into alignment. These techniques enjoy widespread use in a diverse variety of applications, such as video coding, tracking, object and face detection and recognition, surveillance and satellite imaging, medical image analysis and structure from motion. Registration methods are as numerous as their manifold uses, from pixel level and block or feature based methods to Fourier domain methods.

This book is focused on providing algorithms and image and video techniques for registration and quality performance metrics. The authors provide various assessment metrics for measuring registration quality alongside analyses of registration techniques, introducing and explaining both familiar and state-of-the-art registration methodologies used in a variety of targeted applications.

Key features:
- Provides a state-of-the-art review of image and video registration techniques, allowing readers to develop an understanding of how well the techniques perform by using specific quality assessment criteria
- Addresses a range of applications from familiar image and video processing domains to satellite and medical imaging among others, enabling readers to discover novel methodologies with utility in their own research
- Discusses quality evaluation metrics for each application domain with an interdisciplinary approach from different research perspectives

Comparative evaluation of multi-label classification methods

This paper presents a comparative evaluation of popular multi-label classification methods on several multi-label problems from different domains. The methods include multi-label k-nearest neighbor, binary relevance, label power set, random k-label set ensemble learning, calibrated label ranking, hierarchy of multi-label classifiers and triple random ensemble multi-label classification algorithms. These multi-label learning algorithms are evaluated using several widely used MLC evaluation metrics. The evaluation results show that for each multi-label classification problem a particular MLC method can be recommended. The multi-label evaluation datasets used in this study are related to scene images, multimedia video frames, diagnostic medical report, email messages, emotional music data, biological genes and multi-structural proteins categorization.

Dimensions and metrics for evaluating recommendation systems

Recommendation systems support users and developers of various computer and software systems to overcome information overload, perform information discovery tasks, and approximate computation, among others. They have recently become popular and have attracted a wide variety of application scenarios ranging from business process modeling to source code manipulation. Due to this wide variety of application domains, different approaches and metrics have been adopted for their evaluation. In this chapter, we review a range of evaluation metrics and measures as well as some approaches used for evaluating recommendation systems. The metrics presented in this chapter are grouped under sixteen different dimensions, e.g., correctness, novelty, coverage. We review these metrics according to the dimensions to which they correspond. A brief overview of approaches to comprehensive evaluation using collections of recommendation system dimensions and associated metrics is presented. We also provide suggestions for key future research and practice directions.

Metrics for Association Rule Clustering Assessment

Issues related to association mining have received attention, especially the ones aiming to discover and facilitate the search for interesting patterns. A promising approach, in this context, is the application of clustering in the pre-processing step. In this paper, eleven metrics are proposed to provide an assessment procedure in order to support the evaluation of this kind of approach. To propose the metrics, a subjective evaluation was done. The metrics are important since they provide criteria to: (a) analyze the methodologies, (b) identify their positive and negative aspects, (c) carry out comparisons among them and, therefore, (d) help the users to select the most suitable solution for their problems. Besides, the metrics do the users think about aspects related to the problems and provide a flexible way to solve them. Some experiments were done in order to present how the metrics can be used and their usefulness.

Phrase-based statistical machine translation: explanation of its processes and statistical models and evaluation of the English to Spanish translations produced

Statistical machine translation (SMT) is an approach to Machine Translation (MT) that uses statistical models whose parameter estimation is based on the analysis of existing human translations (contained in bilingual corpora). From a translation student’s standpoint, this dissertation aims to explain how a phrase-based SMT system works, to determine the role of the statistical models it uses in the translation process and to assess the quality of the translations provided that system is trained with in-domain goodquality corpora. To that end, a phrase-based SMT system based on Moses has been trained and subsequently used for the English to Spanish translation of two texts related in topic to the training data. Finally, the quality of this output texts produced by the system has been assessed through a quantitative evaluation carried out with three different automatic evaluation measures and a qualitative evaluation based on the Multidimensional Quality Metrics (MQM).

Using interaction data for improving the offline and online evaluation of search engines

This thesis investigates how web search evaluation can be improved using historical interaction data. Modern search engines combine offline and online evaluation approaches in a sequence of steps that a tested change needs to pass through to be accepted as an improvement and subsequently deployed. We refer to such a sequence of steps as an evaluation pipeline. In this thesis, we consider the evaluation pipeline to contain three sequential steps: an offline evaluation step, an online evaluation scheduling step, and an online evaluation step. In this thesis we show that historical user interaction data can aid in improving the accuracy or efficiency of each of the steps of the web search evaluation pipeline. As a result of these improvements, the overall efficiency of the entire evaluation pipeline is increased. Firstly, we investigate how user interaction data can be used to build accurate offline evaluation methods for query auto-completion mechanisms. We propose a family of offline evaluation metrics for query auto-completion that represents the effort the user has to spend in order to submit their query. The parameters of our proposed metrics are trained against a set of user interactions recorded in the search engine’s query logs. From our experimental study, we observe that our proposed metrics are significantly more correlated with an online user satisfaction indicator than the metrics proposed in the existing literature. Hence, fewer changes will pass the offline evaluation step to be rejected after the online evaluation step. As a result, this would allow us to achieve a higher efficiency of the entire evaluation pipeline. Secondly, we state the problem of the optimised scheduling of online experiments. We tackle this problem by considering a greedy scheduler that prioritises the evaluation queue according to the predicted likelihood of success of a particular experiment. This predictor is trained on a set of online experiments, and uses a diverse set of features to represent an online experiment. Our study demonstrates that a higher number of successful experiments per unit of time can be achieved by deploying such a scheduler on the second step of the evaluation pipeline. Consequently, we argue that the efficiency of the evaluation pipeline can be increased. Next, to improve the efficiency of the online evaluation step, we propose the Generalised Team Draft interleaving framework. Generalised Team Draft considers both the interleaving policy (how often a particular combination of results is shown) and click scoring (how important each click is) as parameters in a data-driven optimisation of the interleaving sensitivity. Further, Generalised Team Draft is applicable beyond domains with a list-based representation of results, i.e. in domains with a grid-based representation, such as image search. Our study using datasets of interleaving experiments performed both in document and image search domains demonstrates that Generalised Team Draft achieves the highest sensitivity. A higher sensitivity indicates that the interleaving experiments can be deployed for a shorter period of time or use a smaller sample of users. Importantly, Generalised Team Draft optimises the interleaving parameters w.r.t. historical interaction data recorded in the interleaving experiments. Finally, we propose to apply the sequential testing methods to reduce the mean deployment time for the interleaving experiments. We adapt two sequential tests for the interleaving experimentation. We demonstrate that one can achieve a significant decrease in experiment duration by using such sequential testing methods. The highest efficiency is achieved by the sequential tests that adjust their stopping thresholds using historical interaction data recorded in diagnostic experiments. Our further experimental study demonstrates that cumulative gains in the online experimentation efficiency can be achieved by combining the interleaving sensitivity optimisation approaches, including Generalised Team Draft, and the sequential testing approaches. Overall, the central contributions of this thesis are the proposed approaches to improve the accuracy or efficiency of the steps of the evaluation pipeline: the offline evaluation frameworks for the query auto-completion, an approach for the optimised scheduling of online experiments, a general framework for the efficient online interleaving evaluation, and a sequential testing approach for the online search evaluation. The experiments in this thesis are based on massive real-life datasets obtained from Yandex, a leading commercial search engine. These experiments demonstrate the potential of the proposed approaches to improve the efficiency of the evaluation pipeline.

Statistical Analysis of Text Summarization Evaluation

This dissertation applies statistical methods to the evaluation of automatic summarization using data from the Text Analysis Conferences in 2008-2011. Several aspects of the evaluation framework itself are studied, including the statistical testing used to determine significant differences, the assessors, and the design of the experiment. In addition, a family of evaluation metrics is developed to predict the score an automatically generated summary would receive from a human judge and its results are demonstrated at the Text Analysis Conference. Finally, variations on the evaluation framework are studied and their relative merits considered. An over-arching theme of this dissertation is the application of standard statistical methods to data that does not conform to the usual testing assumptions.

Object tracking using multiple motion modalities

This paper presents an object tracking system that utilises a hybrid multi-layer motion segmentation and optical flow algorithm. While many tracking systems seek to combine multiple modalities such as motion and depth or multiple inputs within a fusion system to improve tracking robustness, current systems have avoided the combination of motion and optical flow. This combination allows the use of multiple modes within the object detection stage. Consequently, different categories of objects, within motion or stationary, can be effectively detected utilising either optical flow, static foreground or active foreground information. The proposed system is evaluated using the ETISEO database and evaluation metrics and compared to a baseline system utilising a single mode foreground segmentation technique. Results demonstrate a significant improvement in tracking results can be made through the incorporation of the additional motion information.

Overview of the NTCIR-9 crosslink task : cross-lingual link discovery

This paper presents an overview of NTCIR-9 Cross-lingual Link Discovery (Crosslink) task. The overview includes: the motivation of cross-lingual link discovery; the Crosslink task definition; the run submission specification; the assessment and evaluation framework; the evaluation metrics; and the evaluation results of submitted runs. Cross-lingual link discovery (CLLD) is a way of automatically finding potential links between documents in different languages. The goal of this task is to create a reusable resource for evaluating automated CLLD approaches. The results of this research can be used in building and refining systems for automated link discovery. The task is focused on linking between English source documents and Chinese, Korean, and Japanese target documents.

The effectiveness of cross-lingual link discovery

This paper describes the evaluation in benchmarking the effectiveness of cross-lingual link discovery (CLLD). Cross lingual link discovery is a way of automatically finding prospective links between documents in different languages, which is particularly helpful for knowledge discovery of different language domains. A CLLD evaluation framework is proposed for system performance benchmarking. The framework includes standard document collections, evaluation metrics, and link assessment and evaluation tools. The evaluation methods described in this paper have been utilised to quantify the system performance at NTCIR-9 Crosslink task. It is shown that using the manual assessment for generating gold standard can deliver a more reliable evaluation result.

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.

A linear programming approach for estimating the structure of a sparse linear genetic network from transcript profiling data

Background: A genetic network can be represented as a directed graph in which a node corresponds to a gene and a directed edge specifies the direction of influence of one gene on another. The reconstruction of such networks from transcript profiling data remains an important yet challenging endeavor. A transcript profile specifies the abundances of many genes in a biological sample of interest. Prevailing strategies for learning the structure of a genetic network from high-dimensional transcript profiling data assume sparsity and linearity. Many methods consider relatively small directed graphs, inferring graphs with up to a few hundred nodes. This work examines large undirected graphs representations of genetic networks, graphs with many thousands of nodes where an undirected edge between two nodes does not indicate the direction of influence, and the problem of estimating the structure of such a sparse linear genetic network (SLGN) from transcript profiling data. Results: The structure learning task is cast as a sparse linear regression problem which is then posed as a LASSO (l1-constrained fitting) problem and solved finally by formulating a Linear Program (LP). A bound on the Generalization Error of this approach is given in terms of the Leave-One-Out Error. The accuracy and utility of LP-SLGNs is assessed quantitatively and qualitatively using simulated and real data. The Dialogue for Reverse Engineering Assessments and Methods (DREAM) initiative provides gold standard data sets and evaluation metrics that enable and facilitate the comparison of algorithms for deducing the structure of networks. The structures of LP-SLGNs estimated from the INSILICO1, INSILICO2 and INSILICO3 simulated DREAM2 data sets are comparable to those proposed by the first and/or second ranked teams in the DREAM2 competition. The structures of LP-SLGNs estimated from two published Saccharomyces cerevisae cell cycle transcript profiling data sets capture known regulatory associations. In each S. cerevisiae LP-SLGN, the number of nodes with a particular degree follows an approximate power law suggesting that its degree distributions is similar to that observed in real-world networks. Inspection of these LP-SLGNs suggests biological hypotheses amenable to experimental verification. Conclusion: A statistically robust and computationally efficient LP-based method for estimating the topology of a large sparse undirected graph from high-dimensional data yields representations of genetic networks that are biologically plausible and useful abstractions of the structures of real genetic networks. Analysis of the statistical and topological properties of learned LP-SLGNs may have practical value; for example, genes with high random walk betweenness, a measure of the centrality of a node in a graph, are good candidates for intervention studies and hence integrated computational – experimental investigations designed to infer more realistic and sophisticated probabilistic directed graphical model representations of genetic networks. The LP-based solutions of the sparse linear regression problem described here may provide a method for learning the structure of transcription factor networks from transcript profiling and transcription factor binding motif data.