The paper proposes an information-theorybased method for feature types analysis in probabilistic evaluation modelling for statistical parsing. The basic idea is that we use entropy and conditional entropy to measure whether a feature type grasps some of the information for syntactic structure prediction. Our experiment quantitatively analyzes several feature types’ power for syntactic structure prediction and draws a series of interesting conclusions.
Previous work on the induction of selectional preferences has been mainly carried out for English and has concentrated almost exclusively on verbs and their direct objects. In this paper, we focus on class-based models of selectional preferences for German verbs and take into account not only direct objects, but also subjects and prepositional complements. We evaluate model performance against human judgments and show that there is no single method that overall performs best.
The research focuses on commercial banks in Vietnam including state-owned commercial banks and other joint stock commercial banks, but foreign banks and joint-venture banks in Vietnam. The research reviews bank data and statistics of more than 40 Vietnamese commercial banks for the period of 2006-2012 and their financial statements in 2012.
Since the seminal study of Leland, Taqqu, Willinger, and Wilson , which set the groundwork for considering self-similarity an important notion in the understanding of network traffic including the modeling and analysis of network performance, an explosion of work has ensued investigating the multifaceted nature of this phenomenon.
Given a collection of records (training set )
Each record contains a set of attributes, one of the attributes is the class.
Find a model for class attribute as a function of the values of other attributes.
Goal: previously unseen records should be assigned a class as accurately as possible.
A test set is used to determine the accuracy of the model. Usually, the given data set is divided into training and test sets, with training set used to build the model and test set used to validate it.
2. The computational inter-relationships between data types are complex: eg rainfall/soil type/location/species. A Generic model can evaluate a variety of separate investment projects for a variety of users.
Bryan Singler is evaluating results for three separate business segments under his control. Selected financial information for each segment follows: Rank order the three segments based on “margin,” “turnover,” and “return on investment.” How is it possible that the rankings differ based on which evaluative model is used?
Having a vision, a mission, and a passion are invariably seen as
conditions for success. The 1995 U.S. Department of Health and
Human Services (DHHS) concept of a Metropolitan Medical Response
System (MMRS) demonstrated that the leaders of DHHS had a
vision for an effective response to a mass-casualty terrorism incident with
a weapon of mass destruction. The mission was to expand the experimental
model of the Metropolitan Medical Strike Team (MMST) established
in Washington, D.C., and neighboring counties into a national
This paper proposes a novel method for learning probability models of subcategorization preference of verbs. We consider the issues of case dependencies and noun class generalization in a uniform way by employing the maximum entropy modeling method. We also propose a new model selection algorithm which starts from the most general model and gradually examines more specific models.
Simulation allows the repeated solution of an evaluation model.
Each solution randomly selects values from predetermined probability distributions.
All solutions are summarized into an overall distribution of NPV values.
This distribution shows management how risky the project is.
survey instruments, modeling exercises, guidelines for practitioners and research professionals, and supporting documentation; or deliver preliminary findings. All RAND reports undergo rigorous peer review to ensure that they meet high standards for research quality and objectivity.
We consider the problem of correcting errors made by English as a Second Language (ESL) writers and address two issues that are essential to making progress in ESL error correction - algorithm selection and model adaptation to the ﬁrst language of the ESL learner. A variety of learning algorithms have been applied to correct ESL mistakes, but often comparisons were made between incomparable data sets. We conduct an extensive, fair comparison of four popular learning methods for the task, reversing conclusions from earlier evaluations. ...
We present a novel model to represent and assess the discourse coherence of text. Our model assumes that coherent text implicitly favors certain types of discourse relation transitions. We implement this model and apply it towards the text ordering ranking task, which aims to discern an original text from a permuted ordering of its sentences.
Active Learning (AL) is typically initialized with a small seed of examples selected randomly. However, when the distribution of classes in the data is skewed, some classes may be missed, resulting in a slow learning progress. Our contribution is twofold: (1) we show that an unsupervised language modeling based technique is effective in selecting rare class examples, and (2) we use this technique for seeding AL and demonstrate that it leads to a higher learning rate. The evaluation is conducted in the context of word sense disambiguation. ...
We investigate the empirical behavior of ngram discounts within and across domains. When a language model is trained and evaluated on two corpora from exactly the same domain, discounts are roughly constant, matching the assumptions of modiﬁed Kneser-Ney LMs. However, when training and test corpora diverge, the empirical discount grows essentially as a linear function of the n-gram count. We adapt a Kneser-Ney language model to incorporate such growing discounts, resulting in perplexity improvements over modiﬁed Kneser-Ney and Jelinek-Mercer baselines. ...
We present a global joint model for lemmatization and part-of-speech prediction. Using only morphological lexicons and unlabeled data, we learn a partiallysupervised part-of-speech tagger and a lemmatizer which are combined using features on a dynamically linked dependency structure of words. We evaluate our model on English, Bulgarian, Czech, and Slovene, and demonstrate substantial improvements over both a direct transduction approach to lemmatization and a pipelined approach, which predicts part-of-speech tags before lemmatization. ...
This paper reports the development of loglinear models for the disambiguation in wide-coverage HPSG parsing. The estimation of log-linear models requires high computational cost, especially with widecoverage grammars. Using techniques to reduce the estimation cost, we trained the models using 20 sections of Penn Treebank. A series of experiments empirically evaluated the estimation techniques, and also examined the performance of the disambiguation models on the parsing of real-world sentences. ...
We present an empirical study of the applicability of Probabilistic Lexicalized Tree Insertion Grammars (PLTIG), a lexicalized counterpart to Probabilistic Context-Free Grammars (PCFG), to problems in stochastic naturallanguage processing. Comparing the performance of PLTIGs with non-hierarchical N-gram models and PCFGs, we show that PLTIG combines the best aspects of both, with language modeling capability comparable to N-grams, and improved parsing performance over its nonlexicalized counterpart. Furthermore, training of PLTIGs displays faster convergence than PCFGs. ...