We show that the frequency of word use is not only determined by the word
length [1] and the average information content [2], but also by its emotional
content.We have analysed three established lexica of affective word usage in
English, German, and Spanish, to verify that these lexica have a neutral,
unbiased, emotional content. Taking into account the frequency of word usage,
we find that words with a positive emotional content are more frequently used.
This lends support to Pollyanna hypothesis [3] that there should be a positive
bias in human expression.

This paper deals with the identification of Multiword Expressions (MWEs) in
Manipuri, a highly agglutinative Indian Language. Manipuri is listed in the
Eight Schedule of Indian Constitution. MWE plays an important role in the
applications of Natural Language Processing(NLP) like Machine Translation, Part
of Speech tagging, Information Retrieval, Question Answering etc. Feature
selection is an important factor in the recognition of Manipuri MWEs using
Conditional Random Field (CRF).

Background: Online news reports are increasingly becoming a source for event
based early warning systems that detect natural disasters. Harnessing the
massive volume of information available from multilingual newswire presents as
many challenges as opportunities due to the patterns of reporting complex
spatiotemporal events. Results: In this article we study the problem of
utilising correlated event reports across languages.

Recent studies have shown strong correlation between social networking data
and national influenza rates. We expanded upon this success to develop an
automated text mining system that classifies Twitter messages in real time into
six syndromic categories based on key terms from a public health ontology.
10-fold cross validation tests were used to compare Naive Bayes (NB) and
Support Vector Machine (SVM) models on a corpus of 7431 Twitter messages. SVM
performed better than NB on 4 out of 6 syndromes.

Machine transliteration is a method for automatically converting words in one
language into phonetically equivalent ones in another language. Machine
transliteration plays an important role in natural language applications such
as information retrieval and machine translation, especially for handling
proper nouns and technical terms. Four machine transliteration models --
grapheme-based transliteration model, phoneme-based transliteration model,
hybrid transliteration model, and correspondence-based transliteration model --
have been proposed by several researchers.

A fundamental requirement of any task-oriented dialogue system is the ability
to generate object descriptions that refer to objects in the task domain. The
subproblem of content selection for object descriptions in task-oriented
dialogue has been the focus of much previous work and a large number of models
have been proposed.

We introduce a stochastic graph-based method for computing relative
importance of textual units for Natural Language Processing. We test the
technique on the problem of Text Summarization (TS). Extractive TS relies on
the concept of sentence salience to identify the most important sentences in a
document or set of documents. Salience is typically defined in terms of the
presence of particular important words or in terms of similarity to a centroid
pseudo-sentence.

For a system to understand natural language, it needs to be able to take
natural language text and answer questions given in natural language with
respect to that text; it also needs to be able to follow instructions given in
natural language. To achieve this, a system must be able to process natural
language and be able to capture the knowledge within that text. Thus it needs
to be able to translate natural language text into a formal language. We
discuss our approach to do this, where the translation is achieved by composing
the meaning of words in a sentence.

This paper focuses on a system, WOLFIE (WOrd Learning From Interpreted
Examples), that acquires a semantic lexicon from a corpus of sentences paired
with semantic representations. The lexicon learned consists of phrases paired
with meaning representations. WOLFIE is part of an integrated system that
learns to transform sentences into representations such as logical database
queries. Experimental results are presented demonstrating WOLFIE's ability to
learn useful lexicons for a database interface in four different natural
languages.

Conversational participants tend to immediately and unconsciously adapt to
each other's language styles: a speaker will even adjust the number of articles
and other function words in their next utterance in response to the number in
their partner's immediately preceding utterance. This striking level of
coordination is thought to have arisen as a way to achieve social goals, such
as gaining approval or emphasizing difference in status. But has the adaptation
mechanism become so deeply embedded in the language-generation process as to
become a reflex?

To facilitate future research in unsupervised induction of syntactic
structure and to standardize best-practices, we propose a tagset that consists
of twelve universal part-of-speech categories. In addition to the tagset, we
develop a mapping from 25 different treebank tagsets to this universal set. As
a result, when combined with the original treebank data, this universal tagset
and mapping produce a dataset consisting of common parts-of-speech for 22
different languages.

Grishin proposed enriching the Lambek calculus with multiplicative
disjunction (par) and coresiduals. Applications to linguistics were discussed
by Moortgat, who spoke of the Lambek-Grishin calculus (LG). In this paper, we
adapt Girard's polarity-sensitive double negation embedding for classical logic
to extract a compositional Montagovian semantics from a display calculus for
focused proof search in LG.

We have developed a full discourse parser in the Penn Discourse Treebank
(PDTB) style. Our trained parser first identifies all discourse and
non-discourse relations, locates and labels their arguments, and then
classifies their relation types. When appropriate, the attribution spans to
these relations are also determined. We present a comprehensive evaluation from
both component-wise and error-cascading perspectives.

In this paper the problems of deriving a taxonomy from a text and
concept-oriented text segmentation are approached. Formal Concept Analysis
(FCA) method is applied to solve both of these linguistic problems. The
proposed segmentation method offers a conceptual view for text segmentation,
using a context-driven clustering of sentences. The Concept-oriented Clustering
Segmentation algorithm (COCS) is based on k-means linear clustering of the
sentences. Experimental results obtained using COCS algorithm are presented.

Patterns of word use both reflect and influence a myriad of human activities
and interactions. Like other entities that reproduce and evolve, words rise or
decline depending upon a complex interplay between fitness and environment.
Using Internet discussion communities as model systems, we show that the word
niche, defined as the extent of the word's association with specific people and
topics, is a strong determinant of changes in word frequency. Previous, a
posteriori, studies have indicated that word frequency is a correlate of word
success at historical time scales.

This paper presents our investigations on emotional state categorization from
speech signals with a psychologically inspired computational model against
human performance under the same experimental setup. Based on psychological
studies, we propose a multistage categorization strategy which allows
establishing an automatic categorization model flexibly for a given emotional
speech categorization task. We apply the strategy to the Serbian Emotional
Speech Corpus (GEES) and the Danish Emotional Speech Corpus (DES), where human
performance was reported in previous psychological studies.

We report on work in progress on extracting lexical simplifications (e.g.,
"collaborate" -> "work together"), focusing on utilizing edit histories in
Simple English Wikipedia for this task. We consider two main approaches: (1)
deriving simplification probabilities via an edit model that accounts for a
mixture of different operations, and (2) using metadata to focus on edits that
are more likely to be simplification operations.

We investigate inflection structure of a synthetic language using Latin as an
example. We construct a bipartite graph in which one group of vertices
correspond to dictionary headwords and the other group to inflected forms
encountered in a given text. Each inflected form is connected to its
corresponding headword, which in some cases in non-unique. The resulting sparse
graph decomposes into a large number of connected components, to be called word
groups. We then show how the concept of the word group can be used to construct
coverage curves of selected Latin texts.

The Right Frontier Constraint (RFC), as a constraint on the attachment of new
constituents to an existing discourse structure, has important implications for
the interpretation of anaphoric elements in discourse and for Machine Learning
(ML) approaches to learning discourse structures. In this paper we provide
strong empirical support for SDRT's version of RFC. The analysis of about 100
doubly annotated documents by five different naive annotators shows that SDRT's
RFC is respected about 95% of the time.

There is much debate over the degree to which language learning is governed
by innate language-specific biases, or acquired through cognition-general
principles. Here we examine the probabilistic language acquisition hypothesis
on three levels: We outline a novel theoretical result showing that it is
possible to learn the exact generative model underlying a wide class of
languages, purely from observing samples of the language.

In the article, the methodology and the principles of the compilation of the
Frequency dictionary for Ivan Franko's novel Dlja domashnjoho ohnyshcha (For
the Hearth) are described. The following statistical parameters of the novel
vocabulary are obtained: variety, exclusiveness, concentration indexes,
correlation between word rank and text coverage, etc. The main quantitative
characteristics of Franko's novels Perekhresni stezhky (The Cross-Paths) and
Dlja domashnjoho ohnyshcha are compared on the basis of their frequency
dictionaries.

In the article, the project of quantitative parametrization of all texts by
Ivan Franko is manifested. It can be made only by using modern computer
techniques after the frequency dictionaries for all Franko's works are
compiled. The paper describes the application spheres, methodology, stages,
principles and peculiarities in the compilation of the frequency dictionary of
the second half of the 19th century - the beginning of the 20th century. The
relation between the Ivan Franko frequency dictionary, explanatory dictionary
of writer's language and text corpus is discussed.

A statistical physics study of punctuation effects on sentence lengths is
presented for written texts: {\it Alice in wonderland} and {\it Through a
looking glass}. The translation of the first text into esperanto is also
considered as a test for the role of punctuation in defining a style, and for
contrasting natural and artificial, but written, languages. Several log-log
plots of the sentence length-rank relationship are presented for the major
punctuation marks. Different power laws are observed with characteristic
exponents.

In this chapter, we assume that systematically studying spatial markers
semantics in language provides a means to reveal fundamental properties and
concepts characterizing conceptual representations of space. We propose a
formal system accounting for the properties highlighted by the linguistic
analysis, and we use these tools for representing the semantic content of
several spatial relations of French. The first part presents a semantic
analysis of the expression of space in French aiming at describing the
constraints that formal representations have to take into account.

We propose a mathematical framework for a unification of the distributional
theory of meaning in terms of vector space models, and a compositional theory
for grammatical types, for which we rely on the algebra of Pregroups,
introduced by Lambek. This mathematical framework enables us to compute the
meaning of a well-typed sentence from the meanings of its constituents.
Concretely, the type reductions of Pregroups are `lifted' to morphisms in a
category, a procedure that transforms meanings of constituents into a meaning
of the (well-typed) whole.

Text documents are complex high dimensional objects. To effectively visualize
such data it is important to reduce its dimensionality and visualize the low
dimensional embedding as a 2-D or 3-D scatter plot. In this paper we explore
dimensionality reduction methods that draw upon domain knowledge in order to
achieve a better low dimensional embedding and visualization of documents. We
consider the use of geometries specified manually by an expert, geometries
derived automatically from corpus statistics, and geometries computed from
linguistic resources.

Hidden Markov models (HMMs) have been successfully applied to automatic
speech recognition for more than 35 years in spite of the fact that a key HMM
assumption -- the statistical independence of frames -- is obviously violated
by speech data. In fact, this data/model mismatch has inspired many attempts to
modify or replace HMMs with alternative models that are better able to take
into account the statistical dependence of frames.

This article presents SLAM, an Automatic Solver for Lexical Metaphors like
?d\'eshabiller* une pomme? (to undress* an apple). SLAM calculates a
conventional solution for these productions. To carry on it, SLAM has to
intersect the paradigmatic axis of the metaphorical verb ?d\'eshabiller*?,
where ?peler? (?to peel?) comes closer, with a syntagmatic axis that comes from
a corpus where ?peler une pomme? (to peel an apple) is semantically and
syntactically regular.

A rhetorical structure tree (RS tree) is a representation of discourse
relations among elementary discourse units (EDUs). A RS tree is very useful to
many text processing tasks employing relationships among EDUs such as text
understanding, summarization, and question answering. Thai language with its
unique linguistic characteristics requires a unique RS tree construction
technique. This paper proposes an approach for Thai RS tree construction which
consists of three major steps: EDU segmentation, Thai RS tree construction, and
discourse relation (DR) identification.

The recent increase in dimensionality of data has thrown a great challenge to
the existing dimensionality reduction methods in terms of their effectiveness.
Dimensionality reduction has emerged as one of the significant preprocessing
steps in machine learning applications and has been effective in removing
inappropriate data, increasing learning accuracy, and improving
comprehensibility. Feature redundancy exercises great influence on the
performance of classification process.

Maximum mutual information (MMI) is a model selection criterion used for
hidden Markov model (HMM) parameter estimation that was developed more than
twenty years ago as a discriminative alternative to the maximum likelihood
criterion for HMM-based speech recognition.

If the use of the apostrophe in contemporary English often marks the Saxon
genitive, it may also indicate the omission of one or more let-ters. Some
writers (wrongly?) use it to mark the plural in symbols or abbreviations,
visual-ised thanks to the isolation of the morpheme "s". This punctuation mark
was imported from the Continent in the 16th century. During the 19th century
its use was standardised. However the rules of its usage still seem problematic
to many, including literate speakers of English.

We are developing electronic dictionaries and transducers for the automatic
processing of the Albanian Language. We will analyze the words inside a linear
segment of text. We will also study the relationship between units of sense and
units of form. The composition of words takes different forms in Albanian. We
have found that morphemes are frequently concatenated or simply juxtaposed or
contracted. The inflected grammar of NooJ allows constructing the dictionaries
of flexed forms (declensions or conjugations).

Accurate systems for extracting Protein-Protein Interactions (PPIs)
automatically from biomedical articles can help accelerate biomedical research.
Biomedical Informatics researchers are collaborating to provide metaservices
and advance the state-of-art in PPI extraction. One problem often neglected by
current Natural Language Processing systems is the characteristic complexity of
the sentences in biomedical literature.

In recent decades, Speech interactive systems gained increasing importance.
To develop Dictation System like Dragon for Indian languages it is most
important to adapt the system to a speaker with minimum training. In this paper
we focus on the importance of creating speech database at syllable units and
identifying minimum text to be considered while training any speech recognition
system. There are systems developed for continuous speech recognition in
English and in few Indian languages like Hindi and Tamil.

Paraphrasing methods recognize, generate, or extract phrases, sentences, or
longer natural language expressions that convey almost the same information.
Textual entailment methods, on the other hand, recognize, generate, or extract
pairs of natural language expressions, such that a human who reads (and trusts)
the first element of a pair would most likely infer that the other element is
also true. Paraphrasing can be seen as bidirectional textual entailment and
methods from the two areas are often very similar.

Phylogenetic trees can be reconstructed from the matrix which contains the
distances between all pairs of languages in a family. Recently, we proposed a
new method which uses normalized Levenshtein distances among words with same
meaning and averages on all the items of a given list. Decisions about the
number of items in the input lists for language comparison have been debated
since the beginning of glottochronology. The point is that words associated to
some of the meanings have a rapid lexical evolution.

A dictionary defines words in terms of other words. Definitions can tell you
the meanings of words you don't know, but only if you know the meanings of the
defining words. How many words do you need to know (and which ones) in order to
be able to learn all the rest from definitions? We reduced dictionaries to
their "grounding kernels" (GKs), about 10% of the dictionary, from which all
the other words could be defined. The GK words turned out to have
psycholinguistic correlates: they were learned at an earlier age and more
concrete than the rest of the dictionary.

A survey of dictionary models and formats is presented as well as a
presentation of corresponding recent standardisation activities.

The idea of measuring distance between languages seems to have its roots in
the work of the French explorer Dumont D'Urville (D'Urville 1832). He collected
comparative words lists of various languages during his voyages aboard the
Astrolabe from 1826 to1829 and, in his work about the geographical division of
the Pacific, he proposed a method to measure the degree of relation among
languages.

A simple method for finding the entropy and redundancy of a reasonable long
sample of English text is presented. In fact, this method can be extended to
other Latin languages. Some implications for practical applications such as
plagiarism-detection software, and the minimum number of words that should be
used in social Internet network messaging, are discussed. Results on the
entropy of the English language have been obtained by direct computer
processing and from first principles according to Shannon theory.

The goal of this paper is two-fold: to present an abstract data model for
linguistic annotations and its implementation using XML, RDF and related
standards; and to outline the work of a newly formed committee of the
International Standards Organization (ISO), ISO/TC 37/SC 4 Language Resource
Management, which will use this work as its starting point.

This paper presents a theoretical research based approach to ellipsis
resolution in machine translation. Moreover, the formula of discourse is
applied in order to resolve ellipses. The validity of the discourse formula is
analyzed by applying it to the real world text i.e. newspaper fragments. The
source text is converted into mono-sentential discourses where complex
discourses require further dissection either directly into primitive discourses
or first into compound discourses and later into primitive ones. The procedure
of dissection needs further improvement i.e.

Artificial Neural Network (ANN) s has widely been used for recognition of
optically scanned character, which partially emulates human thinking in the
domain of the Artificial Intelligence. But prior to recognition, it is
necessary to segment the character from the text to sentences, words etc.
Segmentation of words into individual letters has been one of the major
problems in handwriting recognition. Despite several successful works all over
the work, development of such tools in specific languages is still an ongoing
process especially in the Indian context.

This paper describes a hybrid system for WSD, presented to the English
all-words and lexical-sample tasks, that relies on two different unsupervised
approaches. The first one selects the senses according to mutual information
proximity between a context word a variant of the sense. The second heuristic
analyzes the examples of use in the glosses of the senses so that simple
syntactic patterns are inferred. This patterns are matched against the
disambiguation contexts.

Both syntax-phonology and syntax-semantics interfaces in Higher Order Grammar
(HOG) are expressed as axiomatic theories in higher-order logic (HOL), i.e. a
language is defined entirely in terms of provability in the single logical
system. An important implication of this elegant architecture is that the
meaning of a valid expression turns out to be represented not by a single, nor
even by a few "discrete" terms (in case of ambiguity), but by a "continuous"
set of logically equivalent terms. The note is devoted to precise formulation
and proof of this observation.

There are many scientific problems generated by the multiple and conflicting
alternative definitions of linguistic recursion and human recursive processing
that exist in the literature. The purpose of this article is to make available
to the linguistic community the standard mathematical definition of recursion
and to apply it to discuss linguistic recursion. As a byproduct, we obtain an
insight into certain "soft universals" of human languages, which are related to
cognitive constructs necessary to implement mathematical reasoning, i.e.
mathematical model theory.

This article proposes a method to extract dependency structures from
phrase-structure level parsing with Interaction Grammars. Interaction Grammars
are a formalism which expresses interactions among words using a polarity
system. Syntactical composition is led by the saturation of polarities.
Interactions take place between constituents, but as grammars are lexicalized,
these interactions can be translated at the level of words. Dependency
relations are extracted from the parsing process: every dependency is the
consequence of a polarity saturation.

This paper presents an abstract data model for linguistic annotations and its
implementation using XML, RDF and related standards; and to outline the work of
a newly formed committee of the International Standards Organization (ISO),
ISO/TC 37/SC 4 Language Resource Management, which will use this work as its
starting point. The primary motive for presenting the latter is to solicit the
participation of members of the research community to contribute to the work of
the committee.

Sandhi means to join two or more words to coin new word. Sandhi literally
means `putting together' or combining (of sounds), It denotes all combinatory
sound-changes effected (spontaneously) for ease of pronunciation.
Sandhi-vicheda describes [5] the process by which one letter (whether single or
cojoined) is broken to form two words. Part of the broken letter remains as the
last letter of the first word and part of the letter forms the first letter of
the next letter.

The paper reviews the hurdles while trying to implement the OLAC extension
for Dravidian / Indian languages. The paper further explores the possibilities
which could minimise or solve these problems. In this context, the Chinese
system of text processing and the anusaaraka system are scrutinised.