Design and Implementation of a Tactical Generator for Turkish, a Free Constituent Order LanguageThis thesis describes a tactical generator for Turkish, a free constituent order language, in which the order of the constituents may change according to the information structure of the sentences to…Dilek Zeynep Hakkani·Jul 30, 1996SaveLearn
The Grammar of Sense: Is word-sense tagging much more than part-of-speech tagging?This squib claims that Large-scale Automatic Sense Tagging of text (LAST) can be done at a high-level of accuracy and with far less complexity and computational effort than has been believed until…Yorick Wilks, Mark Stevenson·Jul 26, 1996SaveLearn
Learning Translation Rules From A Bilingual CorpusThis paper proposes a mechanism for learning pattern correspondences between two languages from a corpus of translated sentence pairs. The proposed mechanism uses analogical reasoning between two…Ilyas Cicekli, H. Altay Guvenir·Jul 26, 1996SaveLearn
Building Knowledge Bases for the Generation of Software DocumentationAutomated text generation requires a underlying knowledge base from which to generate, which is often difficult to produce. Software documentation is one domain in which parts of this knowledge base…Cecile Paris, Keith Vander Linden·Jul 25, 1996SaveLearn
New Methods, Current Trends and Software Infrastructure for NLPThe increasing use of `new methods' in NLP, which the NeMLaP conference series exemplifies, occurs in the context of a wider shift in the nature and concerns of the discipline. This paper begins…Hamish Cunningham, Yorick Wilks, Robert J. Gaizauskas·Jul 23, 1996SaveLearn
Applying Winnow to Context-Sensitive Spelling CorrectionMultiplicative weight-updating algorithms such as Winnow have been studied extensively in the COLT literature, but only recently have people started to use them in applications. In this paper, we…Andrew R. Golding, Dan Roth·Jul 19, 1996SaveLearn
Phonological modeling for continuous speech recognition in KoreanA new scheme to represent phonological changes during continuous speech recognition is suggested. A phonological tag coupled with its morphological tag is designed to represent the conditions of…WonIl Lee, Geunbae Lee, Jong-Hyeok Lee·Jul 18, 1996SaveLearn
A Machine Learning Approach to the Classification of Dialogue UtterancesThe purpose of this paper is to present a method for automatic classification of dialogue utterances and the results of applying that method to a corpus. Superficial features of a set of training…Toine Andernach·Jul 16, 1996SaveLearn
Morphological Analysis as Classification: an Inductive-Learning ApproachMorphological analysis is an important subtask in text-to-speech conversion, hyphenation, and other language engineering tasks. The traditional approach to performing morphological analysis is to…Antal van den Bosch, Walter Daelemans, Ton Weijters·Jul 16, 1996SaveLearn
A Divide-and-Conquer Strategy for ParsingIn this paper, we propose a novel strategy which is designed to enhance the accuracy of the parser by simplifying complex sentences before parsing. This approach involves the separate parsing of the…Peh Li Shiuan, Christopher Ting Hian Ann·Jul 16, 1996SaveLearn
Mental State Adjectives: the Perspective of Generative LexiconThis paper focusses on mental state adjectives and offers a unified analysis in the theory of Generative Lexicon (Pustejovsky, 1991, 1995). We show that, instead of enumerating the various syntactic…Pierrette Bouillon·Jul 15, 1996SaveLearn
TSNLP - Test Suites for Natural Language ProcessingThe TSNLP project has investigated various aspects of the construction, maintenance and application of systematic test suites as diagnostic and evaluation tools for NLP applications. The paper…Sabine Lehmann, Stephan Oepen, Sylvie Regnier-Prost et al.·Jul 15, 1996SaveLearn
Natural Language Processing: Structure and ComplexityWe introduce a method for analyzing the complexity of natural language processing tasks, and for predicting the difficulty new NLP tasks. Our complexity measures are derived from the Kolmogorov…Wlodek Zadrozny·Jul 13, 1996SaveLearn
Beyond Word N-GramsWe describe, analyze, and evaluate experimentally a new probabilistic model for word-sequence prediction in natural language based on prediction suffix trees (PSTs). By using efficient data…Fernando C. N. Pereira, Yoram Singer, Naftali Tishby·Jul 13, 1996SaveLearn
Learning Micro-Planning Rules for Preventative ExpressionsBuilding text planning resources by hand is time-consuming and difficult. Certainly, a number of planning architectures and their accompanying plan libraries have been implemented, but while the…Keith Vander Linden, ; Barbara Di Eugenio·Jul 12, 1996SaveLearn
A Corpus Study of Negative Imperatives in Natural Language InstructionsIn this paper, we define the notion of a preventative expression and discuss a corpus study of such expressions in instructional text. We discuss our coding schema, which takes into account both form…Keith Vander Linden, Barbara Di Eugenio·Jul 12, 1996SaveLearn
Unsupervised Discovery of Phonological Categories through Supervised Learning of Morphological RulesWe describe a case study in the application of symbolic machine learning techniques for the discovery of linguistic rules and categories. A supervised rule induction algorithm is used to learn…Walter Daelemans, Peter Berck, Steven Gillis·Jul 11, 1996SaveLearn
MBT: A Memory-Based Part of Speech Tagger-GeneratorWe introduce a memory-based approach to part of speech tagging. Memory-based learning is a form of supervised learning based on similarity-based reasoning. The part of speech tag of a word in a…Walter Daelemans, Jakub Zavrel, Peter Berck et al.·Jul 11, 1996SaveLearn
Pattern-Based Context-Free Grammars for Machine TranslationThis paper proposes the use of ``pattern-based'' context-free grammars as a basis for building machine translation (MT) systems, which are now being adopted as personal tools by a broad range…Koichi Takeda·Jul 11, 1996SaveLearn
Efficient Implementation of a Semantic-based Transfer ApproachThis article gives an overview of a new semantic-based transfer approach developed and applied within the Verbmobil Machine Translation project. We present the declarative transfer formalism and…Michael Dorna, Martin C. Emele·Jul 9, 1996SaveLearn
Semantic-based TransferThis article presents a new semantic-based transfer approach developed and applied within the Verbmobil Machine Translation project. We give an overview of the declarative transfer formalism together…Michael Dorna, Martin C. Emele·Jul 9, 1996SaveLearn
From Submit to Submitted via Submission: On Lexical Rules in Large-Scale Lexicon AcquisitionThis paper deals with the discovery, representation, and use of lexical rules (LRs) during large-scale semi-automatic computational lexicon acquisition. The analysis is based on a set of LRs…Evelyne Viegas, Boyan Onyshkevych, Victor Raskin et al.·Jul 8, 1996SaveLearn
Parallel Replacement in Finite State CalculusThis paper extends the calculus of regular expressions with new types of replacement expressions that enhance the expressiveness of the simple replace operator defined in Karttunen (1995). Parallel…Andre Kempe, Lauri Karttunen·Jul 5, 1996SaveLearn
Head Automata for Speech TranslationThis paper presents statistical language and translation models based on collections of small finite state machines we call ``head automata''. The models are intended to capture the lexical…Hiyan Alshawi·Jul 4, 1996SaveLearn
Head Automata and Bilingual Tiling: Translation with Minimal RepresentationsWe present a language model consisting of a collection of costed bidirectional finite state automata associated with the head words of phrases. The model is suitable for incremental application of…Hiyan Alshawi·Jul 3, 1996SaveLearn