Integrating HMM-Based Speech Recognition With Direct Manipulation In A Multimodal Korean Natural Language InterfaceThis paper presents a HMM-based speech recognition engine and its integration into direct manipulation interfaces for Korean document editor. Speech recognition can reduce typical tedious and…Geunbae Lee, Jong-Hyeok Lee, Sangeok Kim·Nov 18, 1996SaveLearn
Nonuniform Markov modelsA statistical language model assigns probability to strings of arbitrary length. Unfortunately, it is not possible to gather reliable statistics on strings of arbitrary length from a finite corpus.…Eric Sven Ristad, Robert G. Thomas·Nov 16, 1996SaveLearn
Data-Oriented Language Processing. An OverviewDuring the last few years, a new approach to language processing has started to emerge, which has become known under various labels such as "data-oriented parsing", "corpus-based…Rens Bod, Remko Scha·Nov 14, 1996SaveLearn
Unsupervised Language AcquisitionThis thesis presents a computational theory of unsupervised language acquisition, precisely defining procedures for learning language from ordinary spoken or written utterances, with no explicit help…Carl de Marcken·Nov 12, 1996SaveLearn
OT SIMPLE - a construction-kit approach to Optimality Theory implementationThis paper details a simple approach to the implementation of Optimality Theory (OT, Prince and Smolensky 1993) on a computer, in part reusing standard system software. In a nutshell, OT's…Markus Walther·Nov 12, 1996SaveLearn
A Morphology-System and Part-of-Speech Tagger for GermanThis paper presents an integrated tool for German morphology and statistical part-of-speech tagging which aims at making some well established methods widely available. The software is very user…Wolfgang Lezius, Reinhard Rapp, Manfred Wettler·Oct 30, 1996SaveLearn
Learning string edit distanceIn many applications, it is necessary to determine the similarity of two strings. A widely-used notion of string similarity is the edit distance: the minimum number of insertions, deletions, and…Eric Sven Ristad, Peter N. Yianilos·Oct 29, 1996SaveLearn
A Faster Structured-Tag Word-Classification MethodSeveral methods have been proposed for processing a corpus to induce a tagset for the sub-language represented by the corpus. This paper examines a structured-tag word classification method…Min Zhang·Oct 25, 1996SaveLearn
Stochastic Attribute-Value GrammarsProbabilistic analogues of regular and context-free grammars are well-known in computational linguistics, and currently the subject of intensive research. To date, however, no satisfactory…Steven Abney·Oct 23, 1996SaveLearn
Gathering Statistics to Aspectually Classify Sentences with a Genetic AlgorithmThis paper presents a method for large corpus analysis to semantically classify an entire clause. In particular, we use cooccurrence statistics among similar clauses to determine the aspectual class…Eric V. Siegel, Kathleen R. McKeown·Oct 21, 1996SaveLearn
Death and Lightness: Using a Demographic Model to Find Support VerbsSome verbs have a particular kind of binary ambiguity: they can carry their normal, full meaning, or they can be merely acting as a prop for the nominal object. It has been suggested that there is a…Mark Dras, Mike Johnson·Oct 2, 1996SaveLearn
Automatic Detection of Omissions in TranslationsADOMIT is an algorithm for Automatic Detection of OMIssions in Translations. The algorithm relies solely on geometric analysis of bitext maps and uses no linguistic information. This property allows…I. Dan Melamed·Sep 28, 1996SaveLearn
A Geometric Approach to Mapping Bitext CorrespondenceThe first step in most corpus-based multilingual NLP work is to construct a detailed map of the correspondence between a text and its translation. Several automatic methods for this task have been…I. Dan Melamed·Sep 28, 1996SaveLearn
Designing Statistical Language Learners: Experiments on Noun CompoundsThe goal of this thesis is to advance the exploration of the statistical language learning design space. In pursuit of that goal, the thesis makes two main theoretical contributions: (i) it…Mark Lauer·Sep 25, 1996SaveLearn
Discourse Coherence and Shifting Centers in Japanese TextsIn languages such as Japanese, the use of zeros, unexpressed arguments of the verb, in utterances that shift the topic involves a risk that the meaning intended by the speaker may not be…Masayo Iida·Sep 24, 1996SaveLearn
Japanese Discourse and the Process of CenteringThis paper has three aims: (1) to generalize a computational account of the discourse process called centering, (2) to apply this account to discourse processing in Japanese so that it can be…Marilyn Walker, Masayo Iida, Sharon Cote·Sep 24, 1996SaveLearn
Centering in Japanese DiscourseIn this paper we propose a computational treatment of the resolution of zero pronouns in Japanese discourse, using an adaptation of the centering algorithm. We are able to factor language-specific…Marilyn Walker, Masayo Iida, Sharon Cote·Sep 24, 1996SaveLearn
A Principled Framework for Constructing Natural Language Interfaces To Temporal DatabasesMost existing natural language interfaces to databases (NLIDBs) were designed to be used with ``snapshot'' database systems, that provide very limited facilities for manipulating…Ion Androutsopoulos·Sep 23, 1996SaveLearn
Cue Phrase Classification Using Machine LearningCue phrases may be used in a discourse sense to explicitly signal discourse structure, but also in a sentential sense to convey semantic rather than structural information. Correctly classifying cue…Diane J. Litman·Sep 9, 1996SaveLearn
Inferring Acceptance and Rejection in Dialogue by Default Rules of InferenceThis paper discusses the processes by which conversants in a dialogue can infer whether their assertions and proposals have been accepted or rejected by their conversational partners. It expands on…Marilyn A. Walker·Sep 7, 1996SaveLearn
Corrections and Higher-Order UnificationWe propose an analysis of corrections which models some of the requirements corrections place on context. We then show that this analysis naturally extends to the interaction of corrections with…Claire Gardent, Michael Kohlhase, Noor van Neusen·Sep 2, 1996SaveLearn
Isolated-Word Confusion Metrics and the PGPfone AlphabetAlthough the confusion of individual phonemes and features have been studied and analyzed since (Miller and Nicely, 1955), there has been little work done on extending this to a predictive theory of…Patrick Juola·Aug 29, 1996SaveLearn
Phonetic Ambiguity : Approaches, Touchstones, Pitfalls and New ApproachesPhonetic ambiguity and confusibility are bugbears for any form of bottom-up or data-driven approach to language processing. The question of when an input is ``close enough'' to a target word…Patrick Juola·Aug 29, 1996SaveLearn
Using sentence connectors for evaluating MT outputThis paper elaborates on the design of a machine translation evaluation method that aims to determine to what degree the meaning of an original text is preserved in translation, without looking into…Eric M. Visser, Masaru Fuji·Aug 29, 1996SaveLearn
Algorithms for Speech Recognition and Language ProcessingSpeech processing requires very efficient methods and algorithms. Finite-state transducers have been shown recently both to constitute a very useful abstract model and to lead to highly efficient…Mehryar Mohri, Michael Riley, Richard Sproat·Aug 27, 1996SaveLearn