Handwriting Recognition with Fuzzy Linguistic Rules
- Ashutosh Malaviya,Liliane Peters
With fuzzy linguistic rules complex handwriting patterns can be represented in a broad linguistic domain, thus
facilitating a flexible and widely valid recognition scheme. Based on the multi-layered human visual recognition
system a multilevel fuzzy rule based classification system is proposed and explained. The constraints
which influence the structure of this system applied to handwritten symbols are briefly discussed.
In recent years various handwriting recognition methods have been developed for both on-line and off-line applications
. These methods include statistical methods like the hidden Markov model , connective learning
based methods like neural networks and syntactic methods. The advantages of neural networks are automatic
Chart Parsing Head-Driven Phrase Structure Grammar
- Fred Popowich,Carl Vogel
A Prolog chart parser for Head-Driven Phrase Structure Grammar (HPSG) is
described. The HPSG formalism has undergone significant modification since Proudian
and Pollard first introduced an HPSG chart parser in 1985. This paper describes the
impact of these developments on chart parsing methodology. It also presents a critical
evaluation of aspects of HPSG which emerges from our implementation.
Head-Driven Phrase Structure Grammar (HPSG) is in the family of linguistic
theories known as unification grammars (Shieber, 1986). Seiffert (1987) has presented a
system for parsing unification grammars in general, while Proudian and Pollard (1985)
have provided an implementation of HPSG in particular. But, HPSG has undergone quite
CUF - A Formalism for Linguistic Knowledge Representation
- Jochen Dorre,Michael Dorna
We describe the formalism CUF (Comprehensive Unification Formalism), which has been
designed as a tool for writing and making computational use of any kind of linguistic description
ranging from phonology to pragmatics. The motivations for its major design decisions are
CUF is an offspring of the line of theory-neutral universal grammar formalisms like PATRII
83] and STUF-II [BKU88, Dor91, DR91]. Like these it is based on defining feature
structures and relations over these as encodings of linguistic principles and data. However,
it is radically more expressive, since it allows the definition of arbitrary recursive relational
dependencies without tying recursion to phrase structure rules. Complex restrictions needed
Object Oriented Modeling Focused On A Linguistic Approach
- N. Juristo,A. M. Moreno
This article aims to propose an
approach to formalize this process. This method is based on the use of linguistic
information from informal specifications. This information is composed of words which, in
turn, denote elements of an OO modeling, such as classes, properties, etc. These words
have a particular meaning, and their use in the modeling is usually related with that
meaning. So, the objective is to analyze this information from the semantic and syntactic
viewpoint and extract, by means of a formal procedure, the components of an OO system.
This paper presents briefly the proposed approach and is focused on the results of its
application by a...
Extracting Expert Knowledge from Medical Texts
- Marc Weeber,Rein Vos
. In this paper we argue that researchers in Intelligent Data
Analysis (IDA) in Medicine and Pharmacology should consider textual
databases as an additional source of knowledge. We describe
three areas where medical knowledge extraction from textual databases
can be fruitful: finding new applications for existing drugs,
evolution of medical knowledge in time, and drug risk assessment.
We evaluate two textual knowledge extraction methods, where an
IDA approach shows to be robust and efficient compared to a common
computational linguistic one.
One of the goals in Intelligent Data Analysis in Medicine and Pharmacology
is the discovery or extraction of medical knowledge in
computerized data . Most applications use medical databases...
How Spatial Information Connects Visual Perception and Natural Language Generation in Dynamic Environments: Towards a Computational Model
- K Intelligenz,Wissensbasierte Systeme,Leitung Prof,Dr. W. Wahlster,Wolfgang Maa
. Suppose that you are required to describe a route step-bystep
to somebody who does not know the environment. A major question
in this context is what kind of spatial information must be integrated in
a route description. This task generally refers to two cognitive abilities:
Visual perception and natural language. In this domain, a computational
model for the generation of incremental route descriptions is presented.
Central to this model is a distinction into a visual, a linguistic, and
a conceptual-spatial level. Basing on these different levels a software
agent, called MOSES, is introduced who moves through a simulated 3D
environment from a starting-point to a destination. He selects...
Structure Sharing Unification of Disjunctive Feature Descriptions
- Johannes Matiasek
A method is presented which allows for unification of disjunctive feature descriptions
with a minimal amount of copying. This is accomplished by using a lazy
incremental copy technique in combination with a representation of feature descriptions
that allows for distributed disjunctions. The use of context descriptions keeps
disjunctions as local as possible and prevents independent alternatives to interact
unnessecarily, thus helping to avoid redundant copying. In that way structure sharing
is possible between different feature descriptions as well as between disjuncts.
Furthermore the unification algorithm need not consider nondisjunctive parts of a
feature descriptions twice when dealing with alternatives as e.g., in implementations
employing backtracking. This allows for an...
Using Argumentation to Control Lexical Choice: A Functional Unification Implementation
- Michael Elhadad
to Control Lexical Choice:
A Functional Unification Implementation
This thesis investigates the impact of the pragmatic situation on surface generation. It presents new surface
generation techniques that improve on both aspects of surface generation: (1) lexical choice, which consists of
choosing words and their associated syntactic structures and (2) syntactic realization, which consists of combining
these partial structures into grammatical sentences. Because surface generation depends directly on aspects of the
pragmatic situation, these new techniques allow a purely conceptual input to be expressed by a greater variety of
linguistic forms and with more sensitivity to pragmatic factors than was previously possible.
Specifically, this research focuses on...
A Processing Account of Weak Crossover
- Carl Alphonce
this paper I will present a chain-building algorithm and show how it offers an account
of the weak crossover phenomenon. The chain building algorithm is independently
motivated by computational considerations, and is embedded in a psycholinguistically motivated
The paper proceeds as follows: I first present arguments for the reasonably uncontroversial
position that there is a distinction to be made between linguistic competence and
performance. I then outline and motivate my assumptions regarding structure-building in
general and chain-building in particular.
I argue that the existence of so-called garden path utterances is evidence that parsing
does not proceed in a massively parallel fashion. Ranked-parallel models and serial models
A Formal Approach For Generating Oo Specifications From Natural Language
- Natalia Juristo,Jos L. Morant,Ana M. Moreno,Ana Maria Moreno,Facultad De Informatica
The requirements analysis process is essential to software development. The success or failure of a
software system can be said to largely depend on the quality of this activity. A formal and disciplined
process is therefore necessary for requirements analysis. In this paper, we present an approach that is
based on the formal definition of relations between linguistic and OO conceptual structures as a basis for
a formal and disciplined problem analysis process. This process is based on two components, conceptual
model formalization and OO model construction. The first provides formal rules to identify the key
components of conceptual models, and the second, provides a set...
to New Language Pairs
- I. Dan Melamed
There are three steps in porting SIMR to new language pairs. The first step is
to choose an appropriate matching predicate, and collect any linguistic resources
required by that matching predicate. The second step is to implement bitext space
axis generation routines that are consistent with the matching predicate. The last
step is to re-optimize SIMR's numerical parameters. This document explains each
step in detail. It assumes that you have read and understood the paper . It also
assumes that you have SIMR and the porting tools properly installed.
1 Matching Predicate
SIMR's matching predicates can be based on any combination of predicate filters and oracle filters
TDL - A Type Description Language for HPSG Part 1: Overview
- Intelligenz Gmbh,Hans-ulrich Krieger,Ulrich Sch Afer,Deutsches Forschungszentrum,K Unstliche Intelligenz
Unification-based grammar formalisms have become the predominant paradigm in natural
language processing (NLP) and computational linguistics (CL). Their success stems
from the fact that they can be seen as high-level declarative programming languages for
linguists, which allow them to express linguistic knowledge in a monotonic fashion. Moreover,
such formalisms can be given a precise, set-theoretical semantics.
This paper presents TDL, a typed feature-based language and inference system, which
is specifically designed to support highly lexicalized grammar theories like HPSG, FUG,
TDL allows the user to define (possibly recursive) hierarchically-ordered types,
consisting of type constraints and feature constraints over the boolean connectives , ,
and :. TDL distinguishes between...
Scientific Knowledge Discovery using Inductive Logic Programming
- Stephen Muggleton
This paper is an overview of scientific knowledge discovery tasks carried
out using Inductive Logic Programming (ILP). The results reviewed have
been published in some of the top general science journals, and as such are
among the strongest examples of semi-automated scientific discovery in
the Artificial Intelligence literature. Space restrictions do not permit this
paper to cover other discovery areas of ILP. These include the discovery of
linguistic features in natural language data and the discovery of patterns
in traffic data.
The pharmaceutical industry is increasingly overwhelmed by large-volume-data.
This is generated both internally as a side-effect of screening tests and combinatorial
chemistry, as well as externally from sources...
Harmonizing the Approaches
- Robin Cooper,Dick Crouch,Jan Van Eijck,Chris Fox,Josef Van Genabith,Jan Jaspars,Hans Kamp,Manfred Pinkal,Massimo Poesio,Steve Pulman,Espen Vestre,Deliverable D
ion : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : 12
2.3 Quantification : : : : : : : : : : : : : : : : : : : : : : : : : : : : : 15
2.4 Propositions : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : 20
2.5 Predication : : : :...
Automatic Generation of a Fuzzy Rule Base for Online Handwriting Recognition
- Ashutosh Malaviya,Hartmut Surmann,Liliane Peters
An automatic method to generate fuzzy
rules and their membership functions to
recognize handwritten characters is
described. Firstly an initial rule base is created
on the basis of a referential data set
containing handwriting prototypes. Subsequently
the classification behavior of the
fuzzy rules is optimized with a genetic
algorithm, which is regarded as a typical
solution to NP-complete problems. A suitable
fitness function which corresponds to
the human perception of the linguistic
variables is obtained. The proposed rule
generation process extends the learning
and adaptive capabilities of existing fuzzy
rule based recognition system.
Keywords: fuzzy features, fuzzy rule generation,
Online character recognition systems have to
operate in real-time and have to cope with a
multiple number of...
- Enric Vallduv
The Informational Component
Supervisor: Ellen F. Prince
Even though the relevance of non-truth-conditional notions like `topic' and `focus'
in sentence structure and interpretation has long been recognized, there is little
agreement on the exact nature of these notions and their role in a model of linguistic
competence. Following the information-packaging approach (Chafe 1976,
Prince 1986), this study argues that these notions are primitive elements in the
informational component of language. This component, informatics, is responsible
for the articulation of sentences qua information, where information is defined as
that part of propositional content which constitutes a contribution of knowledge
to the hearer's knowledge-store. Informational primitives combine into four possible
Automatic Acquisition of Morphological Knowledge for Medical Language Processing
- Pierre Zweigenbaum,Natalia Grabar
Medical words exhibit a rich and productive morphology. Morphological knowledge is therefore very important for any medical language processing application. We propose a simple and powerful method to acquire automatically such knowledge. It takes advantage of commonly available lists of synonym terms to bootstrap the acquisition process. We experimented it on the SNOMED International Microglossary for pathology in its French version. The families of morphologically related words that we obtained were useful for query expansion in a coding assistant. Since the method does not rely on a priori linguistic knowledge, it is applicable to other languages such as English.
Distributional Clustering Of English Words
- Fernando Pereira,Naftali Tishby,Lillian Lee
We describe and experimentally evaluate a method for
automatically clustering words according to their distribution
in particular syntactic contexts. Deterministic
annealing is used to find lowest distortion sets of
clusters. As the annealing parameter increases, existing
clusters become unstable and subdivide, yielding a
hierarchical "soft" clustering of the data. Clusters are
used as the basis for class models of word coocurrence,
and the models evaluated with respect to held-out test
Methods for automatically classifying words according
to their contexts of use have both scientific and practical
interest. The scientific questions arise in connection
to distributional views of linguistic (particularly
lexical) structure and also in relation to the question
of lexical acquisition both from psychological...
A Dynamic Syntax-Semantics Interface
- Tsutomu Fujinami
The relation between syntax and semantics of natural language
can be regarded as a constraint. With the ideas from Channel Theory
(Barwise 1993, Barwise and Seligman 1994), the way that an utterance
represents a situation can be captured as a linguistic channel. To
study the operational aspects of such a channel, we construct it as a
system of communicating processes by turning to the ß-calculus (Milner
et al. 1992). We show how a concurrent bottom-up chart parser
can be encoded in the calculus and how a semantic object similar to
those employed in Situation Theoretic Discourse Representation Theory
(Cooper 1993) can be created as the result of interactions between
Learning the Rule Base of a Fuzzy Controller by a Genetic Algorithm
- Jorn Hopf,Frank Klawonn
For the design of a fuzzy controller it is necessary to choose,
besides other parameters, suitable membership functions for the
linguistic terms and to determine a rule base.
This paper deals with the problem of finding a good rule base
--- the basis of a fuzzy controller. Consulting experts still is the
usual but time--consuming and therefore rather expensive method.
Besides, after having designed the controller, one cannot be sure
that the rule base will lead to near optimal control. This paper
shows how to reduce significantly the period of development (and
the costs) of fuzzy controllers with the help of genetic algorithms
and, above all, how to engender a...