Treating `Free Word Order' in Machine TranslationIn `free word order' languages, every sentence is embedded in its specific context. Among others, the order of constituents is determined by the categories `theme', `rheme' and…Ralf Steinberger·Sep 8, 1994SaveLearn
Situated Modeling of Epistemic PuzzlesSituation theory is a mathematical theory of meaning introduced by Jon Barwise and John Perry. It has evoked great theoretical and practical interest and motivated the framework of a few…Murat Ersan, Varol Akman·Sep 7, 1994SaveLearn
Focusing for Pronoun Resolution in English Discourse: An ImplementationAnaphora resolution is one of the most active research areas in natural language processing. This study examines focusing as a tool for the resolution of pronouns which are a kind of anaphora.…Ebru Ersan, Varol Akman·Sep 7, 1994SaveLearn
An Experiment on Learning Appropriate Selectional Restrictions from a Parsed CorpusWe present a methodology to extract Selectional Restrictions at a variable level of abstraction from phrasally analyzed corpora. The method relays in the use of a wide-coverage noun taxonomy and a…Francesc Ribas·Sep 7, 1994SaveLearn
Conceptual Association for Compound Noun AnalysisThis paper describes research toward the automatic interpretation of compound nouns using corpus statistics. An initial study aimed at syntactic disambiguation is presented. The approach presented…Mark Lauer·Sep 6, 1994SaveLearn
A Probabilistic Model of Compound NounsCompound nouns such as example noun compound are becoming more common in natural language and pose a number of difficult problems for NLP systems, notably increasing the complexity of parsing. In…Mark Lauer, Mark Dras·Sep 6, 1994SaveLearn
Integrating Knowledge Bases and Statistics in MTWe summarize recent machine translation (MT) research at the Information Sciences Institute of USC, and we describe its application to the development of a Japanese-English newspaper MT system. Our…Kevin Knight, Ishwar Chander, Matthew Haines et al.·Sep 5, 1994SaveLearn
A Unified Process Model of Syntactic and Semantic Error Recovery in Sentence UnderstandingThe development of models of human sentence processing has traditionally followed one of two paths. Either the model posited a sequence of processing modules, each with its own task-specific…Jennifer K. Holbrook, Kurt P. Eiselt, Kavi Mahesh·Aug 31, 1994SaveLearn
Having Your Cake and Eating It Too: Autonomy and Interaction in a Model of Sentence ProcessingIs the human language understander a collection of modular processes operating with relative autonomy, or is it a single integrated process? This ongoing debate has polarized the language processing…Kurt P. Eiselt, Kavi Mahesh, Jennifer K. Holbrook·Aug 31, 1994SaveLearn
Building a Parser That can Afford to Interact with SemanticsNatural language understanding programs get bogged down by the multiplicity of possible syntactic structures while processing real world texts that human understanders do not have much difficulty…Kavi Mahesh·Aug 31, 1994SaveLearn
Uniform Representations for Syntax-Semantics ArbitrationPsychological investigations have led to considerable insight into the working of the human language comprehension system. In this article, we look at a set of principles derived from psychological…Kavi Mahesh, Kurt P. Eiselt·Aug 31, 1994SaveLearn
Reaping the Benefits of Interactive Syntax and SemanticsSemantic feedback is an important source of information that a parser could use to deal with local ambiguities in syntax. However, it is difficult to devise a systematic communication mechanism for…Kavi Mahesh·Aug 31, 1994SaveLearn
On Implementing an HPSG theory -- Aspects of the logical architecture, the formalization, and the implementation of head-driven phrase structure grammarsThe paper presents some aspects involved in the formalization and implementation of HPSG theories. As basis, the logical setups of Carpenter (1992) and King (1989, 1994) are briefly compared…Walt Detmar Meurers·Aug 31, 1994SaveLearn
Experimentally Evaluating Communicative Strategies: The Effect of the TaskEffective problem solving among multiple agents requires a better understanding of the role of communication in collaboration. In this paper we show that there are communicative strategies that…Marilyn A. Walker·Aug 24, 1994SaveLearn
Qualitative and Quantitative Models of Speech TranslationThis paper compares a qualitative reasoning model of translation with a quantitative statistical model. We consider these models within the context of two hypothetical speech translation systems,…Hiyan Alshawi·Aug 24, 1994SaveLearn
Training and Scaling Preference Functions for DisambiguationWe present an automatic method for weighting the contributions of preference functions used in disambiguation. Initial scaling factors are derived as the solution to a least-squares minimization…Hiyan Alshawi, David Carter·Aug 24, 1994SaveLearn
Approximate N-Gram Markov Model for Natural Language GenerationThis paper proposes an Approximate n-gram Markov Model for bag generation. Directed word association pairs with distances are used to approximate (n-1)-gram and n-gram training tables. This model has…Hsin-Hsi Chen, Yue-Shi Lee·Aug 24, 1994SaveLearn
Distributional Clustering of English WordsWe describe and experimentally evaluate a method for automatically clustering words according to their distribution in particular syntactic contexts. Deterministic annealing is used to find lowest…Fernando Pereira, Naftali Tishby, Lillian Lee·Aug 22, 1994SaveLearn
On Using Selectional Restriction in Language Models for Speech RecognitionIn this paper, we investigate the use of selectional restriction -- the constraints a predicate imposes on its arguments -- in a language model for speech recognition. We use an un-tagged corpus,…Joerg P. Ueberla·Aug 19, 1994SaveLearn
Tagging accurately -- Don't guess if you knowWe discuss combining knowledge-based (or rule-based) and statistical part-of-speech taggers. We use two mature taggers, ENGCG and Xerox Tagger, to independently tag the same text and combine the…Pasi Tapanainen, Atro Voutilainen·Aug 16, 1994SaveLearn
Statistical versus symbolic parsing for captioned-information retrievalWe discuss implementation issues of MARIE-1, a mostly symbolic parser fully implemented, and MARIE-2, a more statistical parser partially implemented. They address a corpus of 100,000 picture…Neil C. Rowe·Aug 15, 1994SaveLearn
Emergent Linguistic Rules from Inducing Decision Trees: Disambiguating Discourse Clue WordsWe apply decision tree induction to the problem of discourse clue word sense disambiguation with a genetic algorithm. The automatic partitioning of the training set which is intrinsic to decision…Eric V. Siegel, Kathleen R. McKeown·Aug 13, 1994SaveLearn
LHIP: Extended DCGs for Configurable Robust ParsingWe present LHIP, a system for incremental grammar development using an extended DCG formalism. The system uses a robust island-based parsing method controlled by user-defined performance thresholds.Afzal Ballim, Graham Russell·Aug 3, 1994SaveLearn
A Modular and Flexible Architecture for an Integrated Corpus Query SystemThe paper describes the architecture of an integrated and extensible corpus query system developed at the University of Stuttgart and gives examples of some of the modules realized within this…Oliver Christ·Aug 2, 1994SaveLearn
Parsing with Principles and ProbabilitiesThis paper is an attempt to bring together two approaches to language analysis. The possible use of probabilistic information in principle-based grammars and parsers is considered, including…Andrew Fordham, Matthew Crocker·Aug 2, 1994SaveLearn