Testing for the non-separability of bi-ambiguous compounds

Separability is a concept that is very difficult to define, and yet much of our scientific method is implicitly based upon the assumption that systems can sensibly be reduced to a set of interacting components. This paper examines the notion of separability in the creation of bi-ambiguous compounds that is based upon the CHSH and CH inequalities. It reports results of an experiment showing that violations of the CHSH and CH inequality can occur in human conceptual combination.

Quantum theory beyond the physical : information in context

Measures and theories of information abound, but there are few formalised methods for treating the contextuality that can manifest in different information systems. Quantum theory provides one possible formalism for treating information in context. This paper introduces a quantum-like model of the human mental lexicon, and shows one set of recent experimental data suggesting that concept combinations can indeed behave non-separably. There is some reason to believe that the human mental lexicon displays entanglement.

Semantic oscillations : encoding context and structure in complex valued holographic vectors

In computational linguistics, information retrieval and applied cognition, words and concepts are often represented as vectors in high dimensional spaces computed from a corpus of text. These high dimensional spaces are often referred to as Semantic Spaces. We describe a novel and efficient approach to computing these semantic spaces via the use of complex valued vector representations. We report on the practical implementation of the proposed method and some associated experiments. We also briefly discuss how the proposed system relates to previous theoretical work in Information Retrieval and Quantum Mechanics and how the notions of probability, logic and geometry are integrated within a single Hilbert space representation. In this sense the proposed system has more general application and gives rise to a variety of opportunities for future research.

Overview of the INEX 2010 focused relevance feedback track

The INEX 2010 Focused Relevance Feedback track offered a refined approach to the evaluation of Focused Relevance Feedback algorithms through simulated exhaustive user feedback. As in traditional approaches we simulated a user-in-the loop by re-using the assessments of ad-hoc retrieval obtained from real users who assess focused ad-hoc retrieval submissions. The evaluation was extended in several ways: the use of exhaustive relevance feedback over entire runs; the evaluation of focused retrieval where both the retrieval results and the feedback are focused; the evaluation was performed over a closed set of documents and complete focused assessments; the evaluation was performed over executable implementations of relevance feedback algorithms; and �finally, the entire evaluation platform is reusable. We present the evaluation methodology, its implementation, and experimental results obtained for nine submissions from three participating organisations.

Bayes Factor based speaker segmentation for speaker diarization

This paper proposes the use of the Bayes Factor as a distance metric for speaker segmentation within a speaker diarization system. The proposed approach uses a pair of constant sized, sliding windows to compute the value of the Bayes Factor between the adjacent windows over the entire audio. Results obtained on the 2002 Rich Transcription Evaluation dataset show an improved segmentation performance compared to previous approaches reported in literature using the Generalized Likelihood Ratio. When applied in a speaker diarization system, this approach results in a 5.1% relative improvement in the overall Diarization Error Rate compared to the baseline.

Similarity metrics within a point of view

In vector space based approaches to natural language processing, similarity is commonly measured by taking the angle between two vectors representing words or documents in a semantic space. This is natural from a mathematical point of view, as the angle between unit vectors is, up to constant scaling, the only unitarily invariant metric on the unit sphere. However, similarity judgement tasks reveal that human subjects fail to produce data which satisfies the symmetry and triangle inequality requirements for a metric space. A possible conclusion, reached in particular by Tversky et al., is that some of the most basic assumptions of geometric models are unwarranted in the case of psychological similarity, a result which would impose strong limits on the validity and applicability vector space based (and hence also quantum inspired) approaches to the modelling of cognitive processes. This paper proposes a resolution to this fundamental criticism of of the applicability of vector space models of cognition. We argue that pairs of words imply a context which in turn induces a point of view, allowing a subject to estimate semantic similarity. Context is here introduced as a point of view vector (POVV) and the expected similarity is derived as a measure over the POVV's. Different pairs of words will invoke different contexts and different POVV's. Hence the triangle inequality ceases to be a valid constraint on the angles. We test the proposal on a few triples of words and outline further research.

Information extraction from web services : a comparison of Tokenisation algorithms

Most web service discovery systems use keyword-based search algorithms and, although partially successful, sometimes fail to satisfy some users information needs. This has given rise to several semantics-based approaches that look to go beyond simple attribute matching and try to capture the semantics of services. However, the results reported in the literature vary and in many cases are worse than the results obtained by keyword-based systems. We believe the accuracy of the mechanisms used to extract tokens from the non-natural language sections of WSDL files directly affects the performance of these techniques, because some of them can be more sensitive to noise. In this paper three existing tokenization algorithms are evaluated and a new algorithm that outperforms all the algorithms found in the literature is introduced.

Exponentiated gradient algorithms for conditional random fields and max-margin Markov Networks

Log-linear and maximum-margin models are two commonly-used methods in supervised machine learning, and are frequently used in structured prediction problems. Efficient learning of parameters in these models is therefore an important problem, and becomes a key factor when learning from very large data sets. This paper describes exponentiated gradient (EG) algorithms for training such models, where EG updates are applied to the convex dual of either the log-linear or max-margin objective function; the dual in both the log-linear and max-margin cases corresponds to minimizing a convex function with simplex constraints. We study both batch and online variants of the algorithm, and provide rates of convergence for both cases. In the max-margin case, O(1/ε) EG updates are required to reach a given accuracy ε in the dual; in contrast, for log-linear models only O(log(1/ε)) updates are required. For both the max-margin and log-linear cases, our bounds suggest that the online EG algorithm requires a factor of n less computation to reach a desired accuracy than the batch EG algorithm, where n is the number of training examples. Our experiments confirm that the online algorithms are much faster than the batch algorithms in practice. We describe how the EG updates factor in a convenient way for structured prediction problems, allowing the algorithms to be efficiently applied to problems such as sequence learning or natural language parsing. We perform extensive evaluation of the algorithms, comparing them to L-BFGS and stochastic gradient descent for log-linear models, and to SVM-Struct for max-margin models. The algorithms are applied to a multi-class problem as well as to a more complex large-scale parsing task. In all these settings, the EG algorithms presented here outperform the other methods.

Constructing tag ontology from folksonomy based on WordNet

With the emergence of Web 2.0, Web users can classify Web items of their interest by using tags. Tags reflect users’ understanding to the items collected in each tag. Exploring user tagging behavior provides a promising way to understand users’ information needs. However, free and relatively uncontrolled vocabulary has its drawback in terms of lack of standardization and semantic ambiguity. Moreover, the relationships among tags have not been explored even there exist rich relationships among tags which could provide valuable information for us to better understand users. In this paper, we propose a novel approach to construct tag ontology based on the widely used general ontology WordNet to capture the semantics and the structural relationships of tags. Ambiguity of tags is a challenging problem to deal with in order to construct high quality tag ontology. We propose strategies to find the semantic meanings of tags and a strategy to disambiguate the semantics of tags based on the opinion of WordNet lexicographers. In order to evaluate the usefulness of the constructed tag ontology, in this paper we apply the extracted tag ontology in a tag recommendation experiment. We believe this is the first application of tag ontology for recommendation making. The initial result shows that by using the tag ontology to re-rank the recommended tags, the accuracy of the tag recommendation can be improved.

A task-oriented approach to search engine usability studies

Usability is a multi-dimensional characteristic of a computer system. This paper focuses on usability as a measurement of interaction between the user and the system. The research employs a task-oriented approach to evaluate the usability of a meta search engine. This engine encourages and accepts queries of unlimited size expressed in natural language. A variety of conventional metrics developed by academic and industrial research, including ISO standards,, are applied to the information retrieval process consisting of sequential tasks. Tasks range from formulating (long) queries to interpreting and retaining search results. Results of the evaluation and analysis of the operation log indicate that obtaining advanced search engine results can be accomplished simultaneously with enhancing the usability of the interactive process. In conclusion, we discuss implications for interactive information retrieval system design and directions for future usability research. © 2008 Academy Publisher.

Automated cross-lingual link discovery in Wikipedia

At NTCIR-9, we participated in the cross-lingual link discovery (Crosslink) task. In this paper we describe our approaches to discovering Chinese, Japanese, and Korean (CJK) cross-lingual links for English documents in Wikipedia. Our experimental results show that a link mining approach that mines the existing link structure for anchor probabilities and relies on the “translation” using cross-lingual document name triangulation performs very well. The evaluation shows encouraging results for our system.

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.