When machine translation (MT) knowledge is automatically constructed from bilingual corpora, redundant rules are acquired due to translation variety. These rules increase ambiguity or cause incorrect MT results. To overcome this problem, we constrain the sentences used for knowledge extraction to "the appropriate bilingual sentences for the MT." In this paper, we propose a method using translation literalness to select appropriate sentences or phrases.
The field of machine learning is concerned with the question of how to construct computer programs that automatically improve with experience. In recent years many successful machine learning applications have been developed, ranging from data-mining programs that learn to detect fraudulent credit card transactions, to information-filtering systems that learn users' reading preferences, to autonomous vehicles that learn to drive on public highways. At the same time, there have been important advances in the theory and algorithms that form the foundations of this field....
Surveying with Construction Applications has many contents: Surveying Fundamentals3 Distance Measurement, Surveying Fundamental, Introduction to Total Stations and Theodolites, Total Station Operations, Traverse Surveys and Computations, Satellite Positioning, An Introduction to Geomatics, Machine Guidance and Control, Highway Construction Surveys,...
We study the challenges raised by Arabic verb and subject detection and reordering in Statistical Machine Translation (SMT). We show that post-verbal subject (VS) constructions are hard to translate because they have highly ambiguous reordering patterns when translated to English. In addition, implementing reordering is difﬁcult because the boundaries of VS constructions are hard to detect accurately, even with a state-of-the-art Arabic dependency parser.
Statistical machine translation (SMT) models require bilingual corpora for training, and these corpora are often multilingual with parallel text in multiple languages simultaneously. We introduce an active learning task of adding a new language to an existing multilingual set of parallel text and constructing high quality MT systems, from each language in the collection into this new target language. We show that adding a new language using active learning to the EuroParl corpus provides a signiﬁcant improvement compared to a random sentence selection baseline. ...
We describe a set of supervised machine learning experiments centering on the construction of statistical models of WH-questions. These models, which are built from shallow linguistic features of questions, are employed to predict target variables which represent a user’s informational goals. We report on different aspects of the predictive performance of our models, including the inﬂuence of various training and testing factors on predictive performance, and examine the relationships among the target variables. ...
Statistical methods require very large corpus with high quality. But building large and faultless annotated corpus is a very difficult job. This paper proposes an efficient m e t h o d to construct part-of-speech tagged corpus. A rulebased error correction m e t h o d is proposed to find and correct errors semi-automatically by user-defined rules. We also make use of user's correction log to reflect feedback. Experiments were carried out to show the efficiency of error correction process of this workbench. The result shows that about 63.2 % of tagging errors can be corrected. ...
This lecture introduces you to the fascinating subject of classification and regression with artificial neural networks. In particular, it introduces multi-layer perceptrons (MLPs); teaches you how to combine probability with neural networks so that the nets can be applied to regression, binary classification and multivariate classification; discusses the modular approach to backpropagation and neural network construction in Torch, which was introduced in the previous lecture.
The state-of-the-art system combination method for machine translation (MT) is based on confusion networks constructed by aligning hypotheses with regard to word similarities. We introduce a novel system combination framework in which hypotheses are encoded as a confusion forest, a packed forest representing alternative trees.
This paper presents a method that assists in maintaining a rule-based named-entity recognition and classification system. The underlying idea is to use a separate system, constructed with the use of machine learning, to monitor the performance of the rule-based system. The training data for the second system is generated with the use of the rule-based system, thus avoiding the need for manual tagging. The disagreement of the two systems acts as a signal for updating the rule-based system.
In pro-drop languages, the detection of explicit subjects, zero subjects and nonreferential impersonal constructions is crucial for anaphora and co-reference resolution. While the identiﬁcation of explicit and zero subjects has attracted the attention of researchers in the past, the automatic identiﬁcation of impersonal constructions in Spanish has not been addressed yet and this work is the ﬁrst such study.
With the development of the technology and the way in which human labour is getting minimized and the comforts increasing tremendously the use of electrical energy is ever increasing.... The AC voltages generated may be single phase or 3-phase depending on the power supplied. For low power applications single phase generators are preferable. The basic principles involved in the production of emf and the constructional details of the generators are discussed below.
Necessity of Introducing Some Information Provided by Transformational Analysis into MT Algorithms Irena Bellert Department of English Philology, Warsaw University A few examples of ambiguous English constructions and their Polish equivalents are discussed in terms of the correlation between their respective phrase-marker representations and transformational analyses.
This paper presents a feasibility study for implementing lexical morphology principles in a machine translation system in order to solve unknown words. Multilingual symbolic treatment of word-formation is seducing but requires an in-depth analysis of every step that has to be performed. The construction of a prototype is firstly presented, highlighting the methodological issues of such approach. Secondly, an evaluation is performed on a large set of data, showing the benefits and the limits of such approach. ...
This lecture describes the construction of binary classifiers using a technique called Logistic Regression. The objective is for you to learn: How to apply logistic regression to discriminate between two classes; how to formulate the logistic regression likelihood; how to derive the gradient and Hessian of logistic regression; how to incorporate the gradient vector and Hessian matrix into Newton’s optimization algorithm so as to come up with an algorithm for logistic regression, which we call IRLS.
Construction and operating principles of induction motors are presented in this chapter. The generation of a revolving magnetic field in the stator and torque production in the rotor are described. The per-phase equivalent circuit is introduced for determination of steady-state characteristics of the motor. Operation of the induction machine as a generator is explained.
Certified that the work contained in the thesis entiled "
Verilog-to-C-Compiler: Simulator Generator " by " Anand Vivek Srivastava", has been carried out under my supervision and that this work has not been submitted elsewhere for a degree.
This paper describes a compiler, which converts from Verilog to C. The output is then compiled to machine native code and tends to execute faster than native mode Verilog simulation because the compiler preserves only the synthesis semantics, not the simulation semantics, of Verilog and performs logic minimization.
The FCC uses the term cognitive to mean " adaptive" without requiring machine learning, This text coins the phrase " ideal cognitive radio ( iCR) " for a CR with autonomous machine learning, vision ( not just a camera ), and spoken or written language perception. There will be an exciting progression across aware, adaptive, and cognitive radio ( AACR ). Enjoy!