A Memory-Based Approach to Learning Shallow Natural Language PatternsRecognizing shallow linguistic patterns, such as basic syntactic relationships between words, is a common task in applied natural language and text processing. The common practice for approaching…Shlomo Argamon, Ido Dagan, Yuval Krymolowski·Apr 15, 1999SaveLearn
A Comparison of WordNet and Roget's Taxonomy for Measuring Semantic SimilarityThis paper presents the results of using Roget's International Thesaurus as the taxonomy in a semantic similarity measurement task. Four similarity metrics were taken from the literature and…Michael Mc Hale·Sep 14, 1998SaveLearn
Some Ontological Principles for Designing Upper Level Lexical ResourcesThe purpose of this paper is to explore some semantic problems related to the use of linguistic ontologies in information systems, and to suggest some organizing principles aimed to solve such…Nicola Guarino·Sep 9, 1998SaveLearn
Towards an implementable dependency grammarThe aim of this paper is to define a dependency grammar framework which is both linguistically motivated and computationally parsable. See the demo at http://www.conexor.fi/analysers.html#testingTimo Jarvinen, Pasi Tapanainen·Sep 2, 1998SaveLearn
A Variant of Earley ParsingThe Earley algorithm is a widely used parsing method in natural language processing applications. We introduce a variant of Earley parsing that is based on a ``delayed'' recognition of…Mark-Jan Nederhof, Giorgio Satta·Aug 31, 1998SaveLearn
Segregatory Coordination and Ellipsis in Text GenerationIn this paper, we provide an account of how to generate sentences with coordination constructions from clause-sized semantic representations. An algorithm is developed to generate sentences with…James Shaw·Aug 27, 1998SaveLearn
Error-Driven Pruning of Treebank Grammars for Base Noun Phrase IdentificationFinding simple, non-recursive, base noun phrases is an important subtask for many natural language processing applications. While previous empirical methods for base NP identification have been…Claire Cardie, David Pierce·Aug 26, 1998SaveLearn
Spotting Prosodic Boundaries in Continuous Speech in FrenchA radio speech corpus of 9mn has been prosodically marked by a phonetician expert, and non expert listeners. this corpus is large enough to train and test an automatic boundary spotting system,…V. Pagel, N. Carbonell, Y. Laprie et al.·Aug 26, 1998SaveLearn
Partial Evaluation for Efficient Access to Inheritance LexiconsMultiple default inheritance formalisms for lexicons have attracted much interest in recent years. I propose a new efficient method to access such lexicons. After showing two basic strategies for…Sven Hartrumpf·Aug 25, 1998SaveLearn
Separating Surface Order and Syntactic Relations in a Dependency GrammarThis paper proposes decoupling the dependency tree from word order, such that surface ordering is not determined by traversing the dependency tree. We develop the notion of a word order domain…Norbert Broeker·Aug 25, 1998SaveLearn
Primitive Part-of-Speech Tagging using Word Length and Sentential StructureIt has been argued that, when learning a first language, babies use a series of small clues to aid recognition and comprehension, and that one of these clues is word length. In this paper we present…Simon Cozens·Aug 23, 1998SaveLearn
Letter to Sound Rules for Accented Lexicon CompressionThis paper presents trainable methods for generating letter to sound rules from a given lexicon for use in pronouncing out-of-vocabulary words and as a method for lexicon compression. As the…V. Pagel, K. Lenzo, A. Black·Aug 21, 1998SaveLearn
How to define a context-free backbone for DGs: Implementing a DG in the LFG formalismThis paper presents a multidimensional Dependency Grammar (DG), which decouples the dependency tree from word order, such that surface ordering is not determined by traversing the dependency tree. We…Norbert Broeker·Aug 21, 1998SaveLearn
Deriving the Predicate-Argument Structure for a Free Word Order LanguageIn relatively free word order languages, grammatical functions are intricately related to case marking. Assuming an ordered representation of the predicate-argument structure, this work proposes a…Cem Bozsahin·Aug 20, 1998SaveLearn
Some Properties of Preposition and Subordinate Conjunction AttachmentsDetermining the attachments of prepositions and subordinate conjunctions is a key problem in parsing natural language. This paper presents a trainable approach to making these attachments through…Alexander S. Yeh, Marc B. Vilain·Aug 20, 1998SaveLearn
Isometric Lineation in English Texts: An Empirical and Mathematical Examination of its Character and ConsequencesIn this paper we build on earlier observations and theory regarding word length frequency and sequential distribution to develop a mathematical characterization of some of the language features…Hideaki Aoyama, John Constable·Aug 14, 1998SaveLearn
Combining Expression and Content in Domains for Dialog ManagersWe present work in progress on abstracting dialog managers from their domain in order to implement a dialog manager development tool which takes (among other data) a domain description as input and…Bernd Ludwig, Guenther Goerz, Heinrich Niemann·Aug 13, 1998SaveLearn
Word Length Frequency and Distribution in English: Observations, Theory, and Implications for the Construction of Verse LinesRecent observations in the theory of verse and empirical metrics have suggested that constructing a verse line involves a pattern-matching search through a source text, and that the number of found…Hideaki Aoyama, John Constable·Aug 13, 1998SaveLearn
Parallel Strands: A Preliminary Investigation into Mining the Web for Bilingual TextParallel corpora are a valuable resource for machine translation, but at present their availability and utility is limited by genre- and domain-specificity, licensing restrictions, and the basic…Philip Resnik·Aug 7, 1998SaveLearn
Indexing with WordNet synsets can improve Text RetrievalThe classical, vector space model for text retrieval is shown to give better results (up to 29% better in our experiments) if WordNet synsets are chosen as the indexing space, instead of word forms.…Julio Gonzalo, Felisa Verdejo, Irina Chugur et al.·Aug 5, 1998SaveLearn
An Empirical Evaluation of Probabilistic Lexicalized Tree Insertion GrammarsWe present an empirical study of the applicability of Probabilistic Lexicalized Tree Insertion Grammars (PLTIG), a lexicalized counterpart to Probabilistic Context-Free Grammars (PCFG), to problems…Rebecca Hwa·Aug 4, 1998SaveLearn
Improving Data Driven Wordclass Tagging by System CombinationIn this paper we examine how the differences in modelling between different data driven systems performing the same NLP task can be exploited to yield a higher accuracy than the best individual…Hans van Halteren, Jakub Zavrel, Walter Daelemans·Jul 31, 1998SaveLearn
Character design for soccer commmentaryIn this paper we present early work on an animated talking head commentary system called ByrneDavid Byrne is the lead singer of the Talking Heads.. The goal of this project is to…Kim Binsted·Jul 31, 1998SaveLearn
A Projection Architecture for Dependency Grammar and How it Compares to LFGThis paper explores commonalities and differences between , a variant of Dependency Grammar, and Lexical-Functional Grammar. \ is based on traditional linguistic insights, but on modern…Norbert Broeker·Jul 24, 1998SaveLearn
Statistical Models for Unsupervised Prepositional Phrase AttachmentWe present several unsupervised statistical models for the prepositional phrase attachment task that approach the accuracy of the best supervised methods for this task. Our unsupervised approach uses…Adwait Ratnaparkhi·Jul 22, 1998SaveLearn