Abstract: Many natural language expressions are ambiguous, and
need to draw on other sources of information to be interpreted.
Interpretation of the e word تعاون to be considered as a noun or a verb
depends on the presence of contextual cues. To interpret words we
need to be able to discriminate between different usages. This paper
proposes a hybrid of based- rules and a machine learning method for
tagging Arabic words. The particularity of Arabic word that may be
composed of stem, plus affixes and clitics, a small number of rules
dominate the performance (affixes include inflexional markers for
tense, gender and number/ clitics include some prepositions,
conjunctions and others). Tagging is closely related to the notion of
word class used in syntax. This method is based firstly on rules (that
considered the post-position, ending of a word, and patterns), and
then the anomaly are corrected by adopting a memory-based learning
method (MBL). The memory_based learning is an efficient method to
integrate various sources of information, and handling exceptional
data in natural language processing tasks. Secondly checking the
exceptional cases of rules and more information is made available to
the learner for treating those exceptional cases. To evaluate the
proposed method a number of experiments has been run, and in
order, to improve the importance of the various information in
learning.
Abstract: In this paper a modified version NXM of traditional 5X5 playfair cipher is introduced which enable the user to encrypt message of any Natural language by taking appropriate size of the matrix depending upon the size of the natural language. 5X5 matrix has the capability of storing only 26 characters of English language and unable to store characters of any language having more than 26 characters. To overcome this limitation NXM matrix is introduced which solve this limitation. In this paper a special case of Urdu language is discussed. Where # is used for completing odd pair and * is used for repeating letters.
Abstract: This research uses computational linguistics, an area of study that employs a computer to process natural language, and aims at discerning the patterns that exist in declarative sentences used in technical texts. The approach is mathematical, and the focus is on instructional texts found on web pages. The technique developed by the author and named the MAYA Semantic Technique is used here and organized into four stages. In the first stage, the parts of speech in each sentence are identified. In the second stage, the subject of the sentence is determined. In the third stage, MAYA performs a frequency analysis on the remaining words to determine the verb and its object. In the fourth stage, MAYA does statistical analysis to determine the content of the web page. The advantage of the MAYA Semantic Technique lies in its use of mathematical principles to represent grammatical operations which assist processing and accuracy if performed on unambiguous text. The MAYA Semantic Technique is part of a proposed architecture for an entire web-based intelligent tutoring system. On a sample set of sentences, partial semantics derived using the MAYA Semantic Technique were approximately 80% accurate. The system currently processes technical text in one domain, namely Cµ programming. In this domain all the keywords and programming concepts are known and understood.
Abstract: Text categorization - the assignment of natural language documents to one or more predefined categories based on their semantic content - is an important component in many information organization and management tasks. Performance of neural networks learning is known to be sensitive to the initial weights and architecture. This paper discusses the use multilayer neural network initialization with decision tree classifier for improving text categorization accuracy. An adaptation of the algorithm is proposed in which a decision tree from root node until a final leave is used for initialization of multilayer neural network. The experimental evaluation demonstrates this approach provides better classification accuracy with Reuters-21578 corpus, one of the standard benchmarks for text categorization tasks. We present results comparing the accuracy of this approach with multilayer neural network initialized with traditional random method and decision tree classifiers.
Abstract: Processing the data by computers and performing
reasoning tasks is an important aim in Computer Science. Semantic
Web is one step towards it. The use of ontologies to enhance the
information by semantically is the current trend. Huge amount of
domain specific, unstructured on-line data needs to be expressed in
machine understandable and semantically searchable format.
Currently users are often forced to search manually in the results
returned by the keyword-based search services. They also want to use
their native languages to express what they search. In this paper, an
ontology-based automated question answering system on software
test documents domain is presented. The system allows users to enter
a question about the domain by means of natural language and
returns exact answer of the questions. Conversion of the natural
language question into the ontology based query is the challenging
part of the system. To be able to achieve this, a new algorithm
regarding free text to ontology based search engine query conversion
is proposed. The algorithm is based on investigation of suitable
question type and parsing the words of the question sentence.
Abstract: A computer model of Quantum Theory (QT) has been
developed by the author. Major goal of the computer model was
support and demonstration of an as large as possible scope of QT.
This includes simulations for the major QT (Gedanken-) experiments
such as, for example, the famous double-slit experiment.
Besides the anticipated difficulties with (1) transforming exacting
mathematics into a computer program, two further types of problems
showed up, namely (2) areas where QT provides a complete mathematical
formalism, but when it comes to concrete applications the
equations are not solvable at all, or only with extremely high effort;
(3) QT rules which are formulated in natural language and which do
not seem to be translatable to precise mathematical expressions, nor
to a computer program.
The paper lists problems in all three categories and describes also
the possible solutions or circumventions developed for the computer
model.
Abstract: Term Extraction, a key data preparation step in Text
Mining, extracts the terms, i.e. relevant collocation of words,
attached to specific concepts (e.g. genetic-algorithms and decisiontrees
are terms associated to the concept “Machine Learning" ). In
this paper, the task of extracting interesting collocations is achieved
through a supervised learning algorithm, exploiting a few
collocations manually labelled as interesting/not interesting. From
these examples, the ROGER algorithm learns a numerical function,
inducing some ranking on the collocations. This ranking is optimized
using genetic algorithms, maximizing the trade-off between the false
positive and true positive rates (Area Under the ROC curve). This
approach uses a particular representation for the word collocations,
namely the vector of values corresponding to the standard statistical
interestingness measures attached to this collocation. As this
representation is general (over corpora and natural languages),
generality tests were performed by experimenting the ranking
function learned from an English corpus in Biology, onto a French
corpus of Curriculum Vitae, and vice versa, showing a good
robustness of the approaches compared to the state-of-the-art Support
Vector Machine (SVM).
Abstract: In this paper we propose a computational model for the representation and processing of morpho-phonological phenomena in a natural language, like Modern Greek. We aim at a unified treatment of inflection, compounding, and word-internal phonological changes, in a model that is used for both analysis and generation. After discussing certain difficulties cuase by well-known finitestate approaches, such as Koskenniemi-s two-level model [7] when applied to a computational treatment of compounding, we argue that a morphology-based model provides a more adequate account of word-internal phenomena. Contrary to the finite state approaches that cannot handle hierarchical word constituency in a satisfactory way, we propose a unification-based word grammar, as the nucleus of our strategy, which takes into consideration word representations that are based on affixation and [stem stem] or [stem word] compounds. In our formalism, feature-passing operations are formulated with the use of the unification device, and phonological rules modeling the correspondence between lexical and surface forms apply at morpheme boundaries. In the paper, examples from Modern Greek illustrate our approach. Morpheme structures, stress, and morphologically conditioned phoneme changes are analyzed and generated in a principled way.
Abstract: Text categorization (the assignment of texts in natural language into predefined categories) is an important and extensively studied problem in Machine Learning. Currently, popular techniques developed to deal with this task include many preprocessing and learning algorithms, many of which in turn require tuning nontrivial internal parameters. Although partial studies are available, many authors fail to report values of the parameters they use in their experiments, or reasons why these values were used instead of others. The goal of this work then is to create a more thorough comparison of preprocessing parameters and their mutual influence, and report interesting observations and results.
Abstract: Natural Language Understanding Systems (NLU) will not be widely deployed unless they are technically mature and cost effective to develop. Cost effective development hinges on the availability of tools and techniques enabling the rapid production of NLU applications through minimal human resources. Further, these tools and techniques should allow quick development of applications in a user friendly way and should be easy to upgrade in order to continuously follow the evolving technologies and standards. This paper presents a visual tool for the structuring and editing of dialog forms, the key element of driving conversation in NLU applications based on IBM technology. The main focus is given on the basic component used to describe Human – Machine interactions of that kind, the Dialogue Manager. In essence, the description of a tool that enables the visual representation of the Dialogue Manager mainly during the implementation phase is illustrated.
Abstract: Most of the existing text mining approaches are
proposed, keeping in mind, transaction databases model. Thus, the
mined dataset is structured using just one concept: the “transaction",
whereas the whole dataset is modeled using the “set" abstract type. In
such cases, the structure of the whole dataset and the relationships
among the transactions themselves are not modeled and
consequently, not considered in the mining process.
We believe that taking into account structure properties of
hierarchically structured information (e.g. textual document, etc ...)
in the mining process, can leads to best results. For this purpose, an
hierarchical associations rule mining approach for textual documents
is proposed in this paper and the classical set-oriented mining
approach is reconsidered profits to a Direct Acyclic Graph (DAG)
oriented approach. Natural languages processing techniques are used
in order to obtain the DAG structure. Based on this graph model, an
hierarchical bottom up algorithm is proposed. The main idea is that
each node is mined with its parent node.
Abstract: It is an important task in Korean-English machine
translation to classify the gender of names correctly. When a sentence
is composed of two or more clauses and only one subject is given as a proper noun, it is important to find the gender of the proper noun
for correct translation of the sentence. This is because a singular pronoun has a gender in English while it does not in Korean. Thus,
in Korean-English machine translation, the gender of a proper noun should be determined. More generally, this task can be expanded into the classification of the general Korean names. This paper proposes a statistical method for this problem. By considering a name as just
a sequence of syllables, it is possible to get a statistics for each name from a collection of names. An evaluation of the proposed method
yields the improvement in accuracy over the simple looking-up of the
collection. While the accuracy of the looking-up method is 64.11%, that of the proposed method is 81.49%. This implies that the proposed
method is more plausible for the gender classification of the Korean names.
Abstract: The main aim of this research is to investigate a novel technique for implementing a more natural and intelligent conversation system. Conversation systems are designed to converse like a human as much as their intelligent allows. Sometimes, we can think that they are the embodiment of Turing-s vision. It usually to return a predetermined answer in a predetermined order, but conversations abound with uncertainties of various kinds. This research will focus on an integrated natural language processing approach. This approach includes an integrated knowledge-base construction module, a conversation understanding and generator module, and a state manager module. We discuss effectiveness of this approach based on an experiment.
Abstract: Increasing growth of information volume in the
internet causes an increasing need to develop new (semi)automatic
methods for retrieval of documents and ranking them according to
their relevance to the user query. In this paper, after a brief review
on ranking models, a new ontology based approach for ranking
HTML documents is proposed and evaluated in various
circumstances. Our approach is a combination of conceptual,
statistical and linguistic methods. This combination reserves the
precision of ranking without loosing the speed. Our approach
exploits natural language processing techniques to extract phrases
from documents and the query and doing stemming on words. Then
an ontology based conceptual method will be used to annotate
documents and expand the query. To expand a query the spread
activation algorithm is improved so that the expansion can be done
flexible and in various aspects. The annotated documents and the
expanded query will be processed to compute the relevance degree
exploiting statistical methods. The outstanding features of our
approach are (1) combining conceptual, statistical and linguistic
features of documents, (2) expanding the query with its related
concepts before comparing to documents, (3) extracting and using
both words and phrases to compute relevance degree, (4) improving
the spread activation algorithm to do the expansion based on
weighted combination of different conceptual relationships and (5)
allowing variable document vector dimensions. A ranking system
called ORank is developed to implement and test the proposed
model. The test results will be included at the end of the paper.
Abstract: Due to the ever growing amount of publications about
protein-protein interactions, information extraction from text is
increasingly recognized as one of crucial technologies in
bioinformatics. This paper presents a Protein Interaction Extraction
System using a Link Grammar Parser from biomedical abstracts
(PIELG). PIELG uses linkage given by the Link Grammar Parser to
start a case based analysis of contents of various syntactic roles as
well as their linguistically significant and meaningful combinations.
The system uses phrasal-prepositional verbs patterns to overcome
preposition combinations problems. The recall and precision are
74.4% and 62.65%, respectively. Experimental evaluations with two
other state-of-the-art extraction systems indicate that PIELG system
achieves better performance. For further evaluation, the system is
augmented with a graphical package (Cytoscape) for extracting
protein interaction information from sequence databases. The result
shows that the performance is remarkably promising.
Abstract: Many measures have been proposed for machine
translation evaluation (MTE) while little research has been done on
the performance of MTE methods. This paper is an effort for MTE
performance analysis. A general frame is proposed for the description
of the MTE measure and the test suite, including whether the
automatic measure is consistent with human evaluation, whether
different results from various measures or test suites are consistent,
whether the content of the test suite is suitable for performance
evaluation, the degree of difficulty of the test suite and its influence
on the MTE, the relationship of MTE result significance and the size
of the test suite, etc. For a better clarification of the frame, several
experiment results are analyzed relating human evaluation, BLEU
evaluation, and typological MTE. A visualization method is
introduced for better presentation of the results. The study aims for
aid in construction of test suite and method selection in MTE
practice.
Abstract: With the extensive inclusion of document, especially
text, in the business systems, data mining does not cover the full
scope of Business Intelligence. Data mining cannot deliver its impact
on extracting useful details from the large collection of unstructured
and semi-structured written materials based on natural languages.
The most pressing issue is to draw the potential business intelligence
from text. In order to gain competitive advantages for the business, it
is necessary to develop the new powerful tool, text mining, to expand
the scope of business intelligence.
In this paper, we will work out the strong points of text mining in
extracting business intelligence from huge amount of textual
information sources within business systems. We will apply text
mining to each stage of Business Intelligence systems to prove that
text mining is the powerful tool to expand the scope of BI. After
reviewing basic definitions and some related technologies, we will
discuss the relationship and the benefits of these to text mining. Some
examples and applications of text mining will also be given. The
motivation behind is to develop new approach to effective and
efficient textual information analysis. Thus we can expand the scope
of Business Intelligence using the powerful tool, text mining.
Abstract: In the paper a method of modeling text for Polish is
discussed. The method is aimed at transforming continuous input text
into a text consisting of sentences in so called canonical form, whose
characteristic is, among others, a complete structure as well as no
anaphora or ellipses. The transformation is lossless as to the content
of text being transformed. The modeling method has been worked
out for the needs of the Thetos system, which translates Polish
written texts into the Polish sign language. We believe that the
method can be also used in various applications that deal with the
natural language, e.g. in a text summary generator for Polish.
Abstract: Color categorization is shared among members in a
society. This allows communication of color, especially when using
natural language such as English. Hence sociable robot, to live
coexist with human in human society, must also have the shared
color categorization. To achieve this, many works have been done
relying on modeling of human color perception and mathematical
complexities. In contrast, in this work, the computer as brain of the
robot learns color categorization through interaction with humans
without much mathematical complexities.
Abstract: Named Entity Recognition (NER) aims to classify each word of a document into predefined target named entity classes and is now-a-days considered to be fundamental for many Natural Language Processing (NLP) tasks such as information retrieval, machine translation, information extraction, question answering systems and others. This paper reports about the development of a NER system for Bengali and Hindi using Support Vector Machine (SVM). Though this state of the art machine learning technique has been widely applied to NER in several well-studied languages, the use of this technique to Indian languages (ILs) is very new. The system makes use of the different contextual information of the words along with the variety of features that are helpful in predicting the four different named (NE) classes, such as Person name, Location name, Organization name and Miscellaneous name. We have used the annotated corpora of 122,467 tokens of Bengali and 502,974 tokens of Hindi tagged with the twelve different NE classes 1, defined as part of the IJCNLP-08 NER Shared Task for South and South East Asian Languages (SSEAL) 2. In addition, we have manually annotated 150K wordforms of the Bengali news corpus, developed from the web-archive of a leading Bengali newspaper. We have also developed an unsupervised algorithm in order to generate the lexical context patterns from a part of the unlabeled Bengali news corpus. Lexical patterns have been used as the features of SVM in order to improve the system performance. The NER system has been tested with the gold standard test sets of 35K, and 60K tokens for Bengali, and Hindi, respectively. Evaluation results have demonstrated the recall, precision, and f-score values of 88.61%, 80.12%, and 84.15%, respectively, for Bengali and 80.23%, 74.34%, and 77.17%, respectively, for Hindi. Results show the improvement in the f-score by 5.13% with the use of context patterns. Statistical analysis, ANOVA is also performed to compare the performance of the proposed NER system with that of the existing HMM based system for both the languages.