... that when they are formulated loosely, as in the pre- vious paragraph, they appear to conflict. In par- ticular, in ( 2a) , Right Association seems to call for the parse that makes for Mary a ... syntac- tic, semantic, and lexical rules are applied by a bottom-up all-paths constituent parser to populate a chart with edges containing syntactic, seman- tic, and logical form information. ... unification. Each category has a set of features declared for it. Each fea- ture has a declared value space of possible values (value spaces may be shared by different fea- tures). Feature...
... a long-range research prt~gram rather than as a short-term goal. Motiva!ion Rcasearch on naturallanguage processing sys- tems today strives for the construction of robust and portable systems) ... eliminate arbitrariness. Rather, a definition of representative corpus must take into account tile research goals pursued. For anaturallanguage system which is sup- posed to analyze and ... here allows fora balanced extension of this very smaU core. The list//3 was chosen as the statistical core vocabulary serving as a base for applying se- mantic criteria, becat, se the overall...
... lexicai lookup, syntactic parsing, semantic analysis, and pragmatic analysis. Each stage has been designed to use linguistic data such as the lexicon and grammar, which are maintained separately ... large scale linguistic resources into our natural language understanding system. Client- server architecture was used to make a large volume of lexical information and a large knowledge base ... necessary informationfor many more words than the base system. This information can be extracted at development time, modified if appropriate (for instance, an application may not need all senses...
... i.e. information an advanced userwould get, are available following the advance- information link. The use of semantic relations inmultimedia data, in this case, is hidden in the wayresults are ... analogy to language discourseanalysis for “talking” about multimedia dialectics.It actually borrows terms that are widely used in language analysis for describing a number of phe-nomena (e.g. ... DialecticsKaterina PastraInst. forLanguage & Speech ProcessingAthens, Greecekpastra@ilsp.grEirini BaltaInst. forLanguage & Speech ProcessingAthens, Greeceebalta@ilsp.grAbstractThe growing...
... issues for natural- language systems which serve as interfaces to a database: the problems that arise in a module which maps the meaning representation to a second logical language for expressing ... Shaked - for the many pleasant and productive interactions I have had with them. References [1] Bates, Madeleine and Bobrow, Robert J. A Transportable NaturalLanguageInterfacefor Information ... [3] Codd,E.F. A Relational Model of Data for Large Shared Data Banks. CACM 13(6), June, 1970. [4] Barbara Grosz, Douglas E. Appelt, Paul Martin, and Fernando Pereira. TEAM: An Experiment...
... Linguistics A Comparative Study of Parameter Estimation Methods for Statistical NaturalLanguage Processing Jianfeng Gao*, Galen Andrew*, Mark Johnson*&, Kristina Toutanova* *Microsoft ... Introduction Parameter estimation is fundamental to many sta-tistical approaches to NLP. Because of the high-dimensional nature of natural language, it is often easy to generate an extremely large ... Boosted Lasso The Boosted Lasso (BLasso) algorithm was origi-nally proposed in Zhao and Yu (2004), and was adapted forlanguage modeling by Gao et al. (2006). BLasso can be viewed as a version...
... Johannes Matiasek and Harald Trost + {hannes,georgn~iohn,harald} ~ai.univie.ac.at Austrian Research Institute for Artificial Intelligence (OFAI)* Schotteng. 3, A- 1010 Vienna, Austria +Department ... interfacing between a tactical gen- erator and a speech synthesizer is two-fold: A grammatical description enriched with semantic and pragmatic features has to be translated into a (qualitative) ... candidate positions for both pitch ac- cents and phrasal boundaries are selected. This reflects the fact that though prosody heavily depends on grammaticM and pragmatic factors, its realization...
... Semantic Information Preprocessing for NaturalLanguage Interfaces to Databases Milan Mosny Simon Fraser University Burnaby, BC VhA 1S6, Canada mosny@cs.sfu.ca Abstract An approach is ... utterance in naturallanguage (lexical predicates). Output is a logical formula, consist- ing of predicates meaningful to the database engine (database predicates). AET provides a formalism for ... Edition, Springer- Verlag, New York. Rayner, Manny, 1993. Abductive Equivalentiai Translation and its application to NaturalLanguage Database Interfacing. Ph.D. Thesis, Royal Institute of Technology,...
... new material may be added to planned text are defined on structural grounds. For example, notice that in paragraph 1I from Figure I the language- field is realized as as a compound adjectival ... legitimate ways that the surface structure might be extended: another adjective added to a certain noun phrase, a temporal adjunct added to a clause, another sentence add,~cl tO a paragraph, and ... dictated by the planner. 189 A Computational Theory of Prose Style for NaturalLanguage Generation David D. McDonald and James D. Pnstejovsky Department of Computer and Information Science...
... AnnotationPattern.compile(“pattern”); The method takes advantage of the UIMA im-plementation of annotations. Each annotation is an instance of a class that inherits from the UIMA class Annotation5. UIMA allows ... of an AnnotationPattern is created from the static compile method. AnnotationPattern is analogous to the Java Pattern3 class. AnnotationPattern susceptibilityPattern = AnnotationPattern.compile(“pattern”); ... func-tionality to find annotations that covering the span of another annotations or all annotations contained within the span of another annotation. getContainingAnnotations( Annotation a1 )...
... template-based approach that has been taken in the system, enables the basic language generation algorithms application independent and language independent. At the final stage of language generation ... Generation’, is a branch of computational linguistics, which deals with automatic genera-tion of text in natural human language by the machine. It can be conceptualized as a process leading from a high ... Pradipta Biswas School of Information Technology Indian Institute of Technology, Kharagpur 721302 INDIA pbiswas@sit.iitkgp.ernet.in Abstract Natural Language Generation (NLG) is a way...
... the ACL Student Research Workshop, pages 61–66,Ann Arbor, Michigan, June 2005.c2005 Association for Computational LinguisticsTowards an Optimal Lexicalization in a Natural- Sounding Portable ... frames; frame hierarchy information is provided for each frame, in combination with a list of se-mantically annotated corpus sentences and syntac-tic valence patterns. WordNet is a lexical ... Abstract In contrast to the latest progress in speech recognition, the state-of-the-art in natural language generation for spoken language dialog systems is lagging behind. The core dialog managers...
... lexeme. A particular natu-ral language may have many paradigms. In Eng-lish, alanguage with very little inflectional mor-phology, there are at least two paradigms, a noun paradigm consisting ... 4.1 Candidate Inflection Class Search Space To define a search space wherein inflection classes of anaturallanguage can be identified, my algorithm accepts as input a monolingual corpus for ... the language and proposes candidate mor-pheme boundaries at every character boundary in every word form in the corpus vocabulary. I call each string before a candidate morpheme boundary a candidate...
... search mechanism fora complex database. ã Provide graphical and contextual information for annotation. Annotation is a problem because it still takes a human. ETE offers flexible and easy ... Abstract The NaturalLanguage Understanding Engine Test Environment (ETE) is a GUI software tool that aids in the development and maintenance of large, modular, naturallanguage understanding ... easy access to the intermediate data within and across batch runs. For instance, when grading a semantic analysis, the analyst can bring up the lexical and syntactic analyses of the same sentence,...
... TEXT to answer questions about the information available about an entity, it must have access to the actual database information associated with each entity in the generalization hierarchy. ... domain are good for descriptive purposes, character attributes are better than others as the basis fora breakdown. Attributes with character values can more naturally be the basis fora breakdown ... this information based on the facts in the database. The attribute used to partition the entity class appears as the based DB attribute. The DDAs are a list of actual DB attributes, other than...