Pattern-based topic modelling and its application for information filtering and information retrieval

This thesis targets on a challenging issue that is to enhance users' experience over massive and overloaded web information. The novel pattern-based topic model proposed in this thesis can generate high-quality multi-topic user interest models technically by incorporating statistical topic modelling and pattern mining. We have successfully applied the pattern-based topic model to both fields of information filtering and information retrieval. The success of the proposed model in finding the most relevant information to users mainly comes from its precisely semantic representations to represent documents and also accurate classification of the topics at both document level and collection level.

Searching for people using semantic soft biometric descriptions

It is not uncommon to hear a person of interest described by their height, build, and clothing (i.e. type and colour). These semantic descriptions are commonly used by people to describe others, as they are quick to communicate and easy to understand. However such queries are not easily utilised within intelligent video surveillance systems, as they are difficult to transform into a representation that can be utilised by computer vision algorithms. In this paper we propose a novel approach that transforms such a semantic query into an avatar in the form of a channel representation that is searchable within a video stream. We show how spatial, colour and prior information (person shape) can be incorporated into the channel representation to locate a target using a particle-filter like approach. We demonstrate state-of-the-art performance for locating a subject in video based on a description, achieving a relative performance improvement of 46.7% over the baseline. We also apply this approach to person re-detection, and show that the approach can be used to re-detect a person in a video steam without the use of person detection.

Perfusion fMRI evidence for priming of shared feature-to-lexical connections during cumulative semantic interference in spoken word production

The speed at which target pictures are named increases monotonically as a function of prior retrieval of other exemplars of the same semantic category and is unaffected by the number of intervening items. This cumulative semantic interference effect is generally attributed to three mechanisms: shared feature activation, priming and lexical-level selection. However, at least two additional mechanisms have been proposed: (1) a 'booster' to amplify lexical-level activation and (2) retrieval-induced forgetting (RIF). In a perfusion functional Magnetic Resonance Imaging (fMRI) experiment, we tested hypotheses concerning the involvement of all five mechanisms. Our results demonstrate that the cumulative interference effect is associated with perfusion signal changes in the left perirhinal and middle temporal cortices that increase monotonically according to the ordinal position of exemplars being named. The left inferior frontal gyrus (LIFG) also showed significant perfusion signal changes across ordinal presentations; however, these responses did not conform to a monotonically increasing function. None of the cerebral regions linked with RIF in prior neuroimaging and modelling studies showed significant effects. This might be due to methodological differences between the RIF paradigm and continuous naming as the latter does not involve practicing particular information. We interpret the results as indicating priming of shared features and lexical-level selection mechanisms contribute to the cumulative interference effect, while adding noise to a booster mechanism could account for the pattern of responses observed in the LIFG.

The structure and connectivity of semantic memory in the healthy older adult brain

The anterior temporal lobes (ATLs) have been proposed to serve as a "hub" linking amodal or domain general information about the meaning of words, objects, facts and people distributed throughout the brain in semantic memory. The two primary sources of evidence supporting this proposal, viz. structural imaging studies in semantic dementia (SD) patients and functional imaging investigations, are not without problems. Similarly, knowledge about the anatomo-functional connectivity of semantic memory is limited to a handful of intra-operative electrocortical stimulation (IES) investigations in patients. Here, using principal components analyses (PCA) of a battery of conceptual and non-conceptual tests coupled with voxel based morphometry (VBM) and diffusion tensor imaging (DTI) in a sample of healthy older adults aged 55-85. years, we show that amodal semantic memory relies on a predominantly left lateralised network of grey matter regions involving the ATL, posterior temporal and posterior inferior parietal lobes, with prominent involvement of the left inferior fronto-occipital fasciculus (IFOF) and uncinate fasciculus fibre pathways. These results demonstrate relationships between semantic memory, brain structure and connectivity essential for human communication and cognition.

The semantic interference effect in the picture-word paradigm: An event-related fMRI study employing overt responses

We used event-related functional magnetic resonance imaging (fMRI) to investigate neural responses associated with the semantic interference (SI) effect in the picture-word task. Independent stage models of word production assume that the locus of the SI effect is at the conceptual processing level (Levelt et al. [1999]: Behav Brain Sci 22:1-75), whereas interactive models postulate that it occurs at phonological retrieval (Starreveld and La Heij [1996]: J Exp Psychol Learn Mem Cogn 22:896-918). In both types of model resolution of the SI effect occurs as a result of competitive, spreading activation without the involvement of inhibitory links. These assumptions were tested by randomly presenting participants with trials from semantically-related and lexical control distractor conditions and acquiring image volumes coincident with the estimated peak hemodynamic response for each trial. Overt vocalization of picture names occurred in the absence of scanner noise, allowing reaction time (RT) data to be collected. Analysis of the RT data confirmed the SI effect. Regions showing differential hemodynamic responses during the SI effect included the left mid section of the middle temporal gyrus, left posterior superior temporal gyrus, left anterior cingulate cortex, and bilateral orbitomedial prefrontal cortex. Additional responses were observed in the frontal eye fields, left inferior parietal lobule, and right anterior temporal and occipital cortex. The results are interpreted as indirectly supporting interactive models that allow spreading activation between both conceptual processing and phonological retrieval levels of word production. In addition, the data confirm that selective attention/response suppression has a role in resolving the SI effect similar to the way in which Stroop interference is resolved. We conclude that neuroimaging studies can provide information about the neuroanatomical organization of the lexical system that may prove useful for constraining theoretical models of word production.

Linking business goals to process models in semantic business process modeling

Broad knowledge is required when a business process is modeled by a business analyst. We argue that existing Business Process Management methodologies do not consider business goals at the appropriate level. In this paper we present an approach to integrate business goals and business process models. We design a Business Goal Ontology for modeling business goals. Furthermore, we devise a modeling pattern for linking the goals to process models and show how the ontology can be used in query answering. In this way, we integrate the intentional perspective into our business process ontology framework, enriching the process description and enabling new types of business process analysis. © 2008 IEEE.

Reasoning about natural language phrases for semantic goal driven exploration

This paper presents a symbolic navigation system that uses spatial language descriptions to inform goal-directed exploration in unfamiliar office environments. An abstract map is created from a collection of natural language phrases describing the spatial layout of the environment. The spatial representation in the abstract map is controlled by a constraint based interpretation of each natural language phrase. In goal-directed exploration of an unseen office environment, the robot links the information in the abstract map to observed symbolic information and its grounded world representation. This paper demonstrates the ability of the system, in both simulated and real-world trials, to efficiently find target rooms in environments that it has never been to previously. In three unexplored environments, it is shown that on average the system travels only 8.42% further than the optimal path when using only natural language phrases to complete navigation tasks.

Integrating and evaluating neural word embeddings in information retrieval

Recent advances in neural language models have contributed new methods for learning distributed vector representations of words (also called word embeddings). Two such methods are the continuous bag-of-words model and the skipgram model. These methods have been shown to produce embeddings that capture higher order relationships between words that are highly effective in natural language processing tasks involving the use of word similarity and word analogy. Despite these promising results, there has been little analysis of the use of these word embeddings for retrieval. Motivated by these observations, in this paper, we set out to determine how these word embeddings can be used within a retrieval model and what the benefit might be. To this aim, we use neural word embeddings within the well known translation language model for information retrieval. This language model captures implicit semantic relations between the words in queries and those in relevant documents, thus producing more accurate estimations of document relevance. The word embeddings used to estimate neural language models produce translations that differ from previous translation language model approaches; differences that deliver improvements in retrieval effectiveness. The models are robust to choices made in building word embeddings and, even more so, our results show that embeddings do not even need to be produced from the same corpus being used for retrieval.

Direct estimation of an element of order matrix from H-1 NMR spectra of strongly dipolar coupled spins

NMR spectra of molecules oriented in thermotropic liquid crystalline media provide information on the molecular structure and order. The spins are generally strongly dipolar coupled and the spectral analyse require the tedious and time consuming numerical iterative calculations. The present study demonstrates the application of multiple quantum spin state selective detection of single quantum transitions for mimicking the homonuclear decoupling and the direct estimation of an element of ordering matrix. This information is utilized to estimate the nearly accurate starting dipolar couplings for iterative calculations. The studies on the spectra of strongly dipolar coupled five and six interacting spin systems are reported.

Semantic Classes in Topic Detection and Tracking

Topic detection and tracking (TDT) is an area of information retrieval research the focus of which revolves around news events. The problems TDT deals with relate to segmenting news text into cohesive stories, detecting something new, previously unreported, tracking the development of a previously reported event, and grouping together news that discuss the same event. The performance of the traditional information retrieval techniques based on full-text similarity has remained inadequate for online production systems. It has been difficult to make the distinction between same and similar events. In this work, we explore ways of representing and comparing news documents in order to detect new events and track their development. First, however, we put forward a conceptual analysis of the notions of topic and event. The purpose is to clarify the terminology and align it with the process of news-making and the tradition of story-telling. Second, we present a framework for document similarity that is based on semantic classes, i.e., groups of words with similar meaning. We adopt people, organizations, and locations as semantic classes in addition to general terms. As each semantic class can be assigned its own similarity measure, document similarity can make use of ontologies, e.g., geographical taxonomies. The documents are compared class-wise, and the outcome is a weighted combination of class-wise similarities. Third, we incorporate temporal information into document similarity. We formalize the natural language temporal expressions occurring in the text, and use them to anchor the rest of the terms onto the time-line. Upon comparing documents for event-based similarity, we look not only at matching terms, but also how near their anchors are on the time-line. Fourth, we experiment with an adaptive variant of the semantic class similarity system. The news reflect changes in the real world, and in order to keep up, the system has to change its behavior based on the contents of the news stream. We put forward two strategies for rebuilding the topic representations and report experiment results. We run experiments with three annotated TDT corpora. The use of semantic classes increased the effectiveness of topic tracking by 10-30\% depending on the experimental setup. The gain in spotting new events remained lower, around 3-4\%. The anchoring the text to a time-line based on the temporal expressions gave a further 10\% increase the effectiveness of topic tracking. The gains in detecting new events, again, remained smaller. The adaptive systems did not improve the tracking results.

Find my office: Navigating real space from semantic descriptions

This paper shows that by using only symbolic language phrases, a mobile robot can purposefully navigate to specified rooms in previously unexplored environments. The robot intelligently organises a symbolic language description of the unseen environment and “imagines” a representative map, called the abstract map. The abstract map is an internal representation of the topological structure and spatial layout of symbolically defined locations. To perform goal-directed exploration, the abstract map creates a high-level semantic plan to reason about spaces beyond the robot’s known world. While completing the plan, the robot uses the metric guidance provided by a spatial layout, and grounded observations of door labels, to efficiently guide its navigation. The system is shown to complete exploration in unexplored spaces by travelling only 13.3% further than the optimal path.

Explorations in the distributional and semantic similarity of words

A straightforward computation of the list of the words (the `tail words' of the list) that are distributionally most similar to a given word (the `head word' of the list) leads to the question: How semantically similar to the head word are the tail words; that is: how similar are their meanings to its meaning? And can we do better? The experiment was done on nearly 18,000 most frequent nouns in a Finnish newsgroup corpus. These nouns are considered to be distributionally similar to the extent that they occur in the same direct dependency relations with the same nouns, adjectives and verbs. The extent of the similarity of their computational representations is quantified with the information radius. The semantic classification of head-tail pairs is intuitive; some tail words seem to be semantically similar to the head word, some do not. Each such pair is also associated with a number of further distributional variables. Individually, their overlap for the semantic classes is large, but the trained classification-tree models have some success in using combinations to predict the semantic class. The training data consists of a random sample of 400 head-tail pairs with the tail word ranked among the 20 distributionally most similar to the head word, excluding names. The models are then tested on a random sample of another 100 such pairs. The best success rates range from 70% to 92% of the test pairs, where a success means that the model predicted my intuitive semantic class of the pair. This seems somewhat promising when distributional similarity is used to capture semantically similar words. This analysis also includes a general discussion of several different similarity formulas, arranged in three groups: those that apply to sets with graded membership, those that apply to the members of a vector space, and those that apply to probability mass functions.

Geometric quantum computation using fictitious spin-1/2 subspaces of strongly dipolar coupled nuclear spins

Geometric phases have been used in NMR to implement controlled phase shift gates for quantum-information processing, only in weakly coupled systems in which the individual spins can be identified as qubits. In this work, we implement controlled phase shift gates in strongly coupled systems by using nonadiabatic geometric phases, obtained by evolving the magnetization of fictitious spin-1/2 subspaces, over a closed loop on the Bloch sphere. The dynamical phase accumulated during the evolution of the subspaces is refocused by a spin echo pulse sequence and by setting the delay of transition selective pulses such that the evolution under the homonuclear coupling makes a complete 2 pi rotation. A detailed theoretical explanation of nonadiabatic geometric phases in NMR is given by using single transition operators. Controlled phase shift gates, two qubit Deutsch-Jozsa algorithm, and parity algorithm in a qubit-qutrit system have been implemented in various strongly dipolar coupled systems obtained by orienting the molecules in liquid crystal media.

Construction of energy-level diagram of oriented benzene using connectivity information obtained by modified z-cosy experiment

Experiments involving selective perturbation of a transition yield information about the directly connected transitions, which in turn yield information for deriving the parameters of the spin Hamiltonian of oriented molecules. Problems involved with selective perturbation are removed by the use of a two-dimensional experiment, namely, the modified Z-COSY-experiment, The use of this experiment is demonstrated for obtaining the connectivity information and for determining the parameters of the spin Hamiltonian of oriented benzene, a strongly coupled six-spin system