As natural language understanding research advances towards deeper knowledge modeling, the tasks become more and more complex: we are interested in more nuanced word characteristics, more linguistic properties, deeper semantic and syntactic features. One such example, explored in this article, is the mention detection and recognition task in the Automatic Content Extraction project, with the goal of identifying named, nominal or pronominal references to real-world entities—mentions— and labeling them with three types of information: entity type, entity subtype and mention type. ...
Lecture "Chapter 5: Modeling systems requirements - Events and things" provides students with the knowledge: Models and modeling, types of models, overview of models used in analysis and design, types of models, overview of models used in analysis and design,... Invite you to consult.
MTMF combines the best parts of the Linear Spectral Mixing model and the statistical
Matched Filter model while avoiding the drawbacks of each parent method (Boardman,
1998). It is a useful Matched Filter method without knowing all the possible endmembers in
a landscape especially in case of subtle, sub-pixel occurrences. Firstly, pixel spectra and
endmember spectra require a minimum noise fraction (MNF) (Green et al., 1988, Boardman,
1993) transformation. MNF reduces and separates an image into its most dimensional and
The cost of operating a building far exceeds the cost of constructing it, and yet until recently little attention was paid to the impact of solar radiation on the costs of heating, cooling and ventilation. And now that there has been a surge in interest in energy efficiency and solar design, architects and designers need a practical guide to the modelling and application of solar energy data.
It is intended that this book be suitable for a variety of engineers and ecologists, who
may wish to gain an introduction to the rapidly growing field of ecological and
environmental modelling. An understanding of the fundamentals of environmental
problems and ecology, as presented for instance in the textbook Principles of
Environmental Science and Technology is assumed. Furthermore, it is assumed that
the reader has either a fundamental knowledge of differential equations and matrix
calculations or has read the Appendix, which gives a brief introduction to these
This research examines how differences in the organization of brand information in memory between higher and lower knowledge consumers affects which brands are retrieved when consumers are provided with a usage situation. A spreading activation network model of memory is used to predict the results of an experiment where the usage situations were varied at encoding and repeated recall sessions.
Abstract Although gait change is considered a useful indicator of severity in animal models of Parkinson's disease, systematic and extensive gait analysis in animal models of neurological deficits is not well established. The CatWalk-assisted automated gait analysis system provides a comprehensive way to assess a number of dynamic and static gait parameters simultaneously. In this study, we used the Catwalk system to investigate changes in gait parameters in adult rats with unilateral 6-OHDA-induced lesions and the...
What are the compelling reasons for carrying out dynamic speech modeling? We provide the answer in two related aspects. First, scientific inquiry into the human speech code has been relentlessly pursued for several decades. As an essential carrier of human intelligence and knowledge, speech is the most natural form of human communication. Embedded in the speech code are linguistic (as well as para-linguistic) messages, which are conveyed through four levels of the speech chain.
This paper presents a detailed study of the integration of knowledge from both dependency parses and hierarchical word ontologies into a maximum-entropy-based tagging model that simultaneously labels words with both syntax and semantics. Our ﬁndings show that information from both these sources can lead to strong improvements in overall system accuracy: dependency knowledge improved performance over all classes of word, and knowledge of the position of a word in an ontological hierarchy increased accuracy for words not seen in the training data. ...
A topic model outputs a set of multinomial distributions over words for each topic. In this paper, we investigate the value of bilingual topic models, i.e., a bilingual Latent Dirichlet Allocation model for ﬁnding translations of terms in comparable corpora without using any linguistic resources. Experiments on a document-aligned English-Italian Wikipedia corpus conﬁrm that the developed methods which only use knowledge from word-topic distributions outperform methods based on similarity measures in the original word-document space.
Sentiment classiﬁcation refers to the task of automatically identifying whether a given piece of text expresses positive or negative opinion towards a subject at hand. The proliferation of user-generated web content such as blogs, discussion forums and online review sites has made it possible to perform large-scale mining of public opinion. Sentiment modeling is thus becoming a critical component of market intelligence and social media technologies that aim to tap into the collective wisdom of crowds.
We describe the early stage of our methodology of knowledge acquisition from technical texts. First, a partial morpho-syntactic analysis is performed to extract "candidate terms". Then, the knowledge engineer, assisted by an automatic clustering tool, builds the "conceptual fields" of the domain. We focus on this conceptual analysis stage, describe the data prepared from the results of the morpho-syntactic analysis and show the results of the clustering module and their interpretation.
In the quest for knowledge, it is not uncommon for researchers to push the limits
of simulation techniques to the point where they have to be adapted or totally new
techniques or approaches become necessary. True multiscale modeling techniques
are becoming increasingly necessary given the growing interest in materials and
processes on which large-scale properties are dependent or that can be tuned by their
low-scale properties. An example would be nanocomposites, where embedded nanostructures
completely change the matrix properties due to effects occurring at the
Human embryonic stem cells (hESCs) and induced pluripotent stem cells
are excellent models for the study of embryonic hematopoiesis in vitro,
aiding the design of new differentiation models that may be applicable to
Cross-document coreference, the task of grouping all the mentions of each entity in a document collection, arises in information extraction and automated knowledge base construction. For large collections, it is clearly impractical to consider all possible groupings of mentions into distinct entities.
We present a preliminary study on unsupervised preposition sense disambiguation (PSD), comparing different models and training techniques (EM, MAP-EM with L0 norm, Bayesian inference using Gibbs sampling). To our knowledge, this is the ﬁrst attempt at unsupervised preposition sense disambiguation.
We propose a cascaded linear model for joint Chinese word segmentation and partof-speech tagging. With a character-based perceptron as the core, combined with realvalued features such as language models, the cascaded model is able to efﬁciently utilize knowledge sources that are inconvenient to incorporate into the perceptron directly. Experiments show that the cascaded model achieves improved accuracies on both segmentation only and joint segmentation and part-of-speech tagging. On the Penn Chinese Treebank 5.0, we obtain an error reduction of 18.
In this paper, we propose a linguistically annotated reordering model for BTG-based statistical machine translation. The model incorporates linguistic knowledge to predict orders for both syntactic and non-syntactic phrases. The linguistic knowledge is automatically learned from source-side parse trees through an annotation algorithm. We empirically demonstrate that the proposed model leads to a signiﬁcant improvement of 1.55% in the BLEU score over the baseline reordering model on the NIST MT-05 Chinese-to-English translation task. ...
We would like to draw attention to Hidden Markov Tree Models (HMTM), which are to our knowledge still unexploited in the ﬁeld of Computational Linguistics, in spite of highly successful Hidden Markov (Chain) Models. In dependency trees, the independence assumptions made by HMTM correspond to the intuition of linguistic dependency. Therefore we suggest to use HMTM and tree-modiﬁed Viterbi algorithm for tasks interpretable as labeling nodes of dependency trees.