A Spanish Tagset for the CRATER ProjectThis working paper describes the Spanish tagset to be used in the context of CRATER, a CEC funded project aiming at the creation of a multilingual (English, French, Spanish) aligned corpus using the…Fernando Sánchez León·Jun 14, 1994SaveLearn
An implemented model of punning riddlesIn this paper, we discuss a model of simple question-answer punning, implemented in a program, JAPE, which generates riddles from humour-independent lexical entries. The model uses two main types of…Kim Binsted, Graeme Ritchie·Jun 13, 1994SaveLearn
A symbolic description of punning riddles and its computer implementationRiddles based on simple puns can be classified according to the patterns of word, syllable or phrase similarity they depend upon. We have devised a formal model of the semantic and syntactic…Kim Binsted, Graeme Ritchie·Jun 13, 1994SaveLearn
A Complete and Recursive Feature TheoryVarious feature descriptions are being employed in logic programming languages and constrained-based grammar formalisms. The common notational primitive of these descriptions are functional…Rolf Backofen, Gert Smolka·Jun 10, 1994SaveLearn
DPOCL: A Principled Approach to Discourse PlanningResearch in discourse processing has identified two representational requirements for discourse planning systems. First, discourse plans must adequately represent the intentional structure of the…R. Michael Young, Johanna D. Moore·Jun 10, 1994SaveLearn
TDL--- A Type Description Language for Constraint-Based GrammarsThis paper presents , a typed feature-based representation language and inference system. Type definitions in \ consist of type and feature constraints over the boolean connectives. \…Hans-Ulrich Krieger, Ulrich Schäfer·Jun 8, 1994SaveLearn
An Automatic Method of Finding Topic BoundariesThis article outlines a new method of locating discourse boundaries based on lexical cohesion and a graphical technique called dotplotting. The application of dotplotting to discourse segmentation…Jeffrey C. Reynar·Jun 7, 1994SaveLearn
Corpus-Driven Knowledge Acquisition for Discourse AnalysisThe availability of large on-line text corpora provides a natural and promising bridge between the worlds of natural language processing (NLP) and machine learning (ML). In recent years, the NLP…Stephen Soderland, Wendy Lehnert·Jun 7, 1994SaveLearn
Statistical Augmentation of a Chinese Machine-Readable DictionaryWe describe a method of using statistically-collected Chinese character groups from a corpus to augment a Chinese dictionary. The method is particularly useful for extracting domain-specific and…Pascale Fung, Dekai Wu·Jun 7, 1994SaveLearn
A Hybrid Reasoning Model for Indirect AnswersThis paper presents our implemented computational model for interpreting and generating indirect answers to Yes-No questions. Its main features are 1) a discourse-plan-based approach to implicature,…Nancy Green, Sandra Carberry·Jun 7, 1994SaveLearn
Graded Unification: A Framework for Interactive ProcessingAn extension to classical unification, called graded unification is presented. It is capable of combining contradictory information. An interactive processing paradigm and parser based on this…Albert Kim·Jun 5, 1994SaveLearn
Self-Organizing Machine Translation: Example-Driven Induction of Transfer FunctionsWith the advent of faster computers, the notion of doing machine translation from a huge stored database of translation examples is no longer unreasonable. This paper describes an attempt to merge…Patrick Juola·Jun 3, 1994SaveLearn
Exploring the Statistical Derivation of Transformational Rule Sequences for Part-of-Speech TaggingEric Brill has recently proposed a simple and powerful corpus-based language modeling approach that can be applied to various tasks including part-of-speech tagging and building phrase structure…Lance A. Ramshaw, Mitchell P. Marcus·Jun 3, 1994SaveLearn
Some Advances in Transformation-Based Part of Speech TaggingMost recent research in trainable part of speech taggers has explored stochastic tagging. While these taggers obtain high accuracy, linguistic information is captured indirectly, typically in tens of…Eric Brill·Jun 2, 1994SaveLearn
Multiset-Valued Linear Index Grammars: Imposing Dominance Constraints on DerivationsThis paper defines multiset-valued linear index grammar and unordered vector grammar with dominance links. The former models certain uses of multiset-valued feature structures in unification-based…Owen Rambow·Jun 2, 1994SaveLearn
Parsing Turkish with the Lexical Functional Grammar FormalismThis paper describes our work on parsing Turkish using the lexical-functional grammar formalism. This work represents the first significant effort for parsing Turkish. Our implementation is based on…Zelal Gungordu, Kemal Oflazer·Jun 2, 1994SaveLearn
Aligning a Parallel English-Chinese Corpus Statistically with Lexical CriteriaWe describe our experience with automatic alignment of sentences in parallel English-Chinese texts. Our report concerns three related topics: (1) progress on the HKUST English-Chinese Parallel…Dekai Wu·Jun 2, 1994SaveLearn
Detecting and Correcting Speech RepairsInteractive spoken dialog provides many new challenges for spoken language systems. One of the most critical is the prevalence of speech repairs. This paper presents an algorithm that detects and…Peter Heeman, James Allen·Jun 1, 1994SaveLearn
Word-Sense Disambiguation Using Decomposable ModelsMost probabilistic classifiers used for word-sense disambiguation have either been based on only one contextual feature or have used a model that is simply assumed to characterize the…Rebecca Bruce, Janyce Wiebe·Jun 1, 1994SaveLearn
Towards a Principled Representation of Discourse PlansWe argue that discourse plans must capture the intended causal and decompositional relations between communicative actions. We present a planning algorithm, DPOCL, that builds plan structures that…R. Michael Young, Johanna D. Moore, Martha E. Pollack·Jun 1, 1994SaveLearn
A Learning Approach to Natural Language UnderstandingIn this paper we propose a learning paradigm for the problem of understanding spoken language. The basis of the work is in a formalization of the understanding problem as a communication problem.…Roberto Pieraccini, Esther Levin·Jun 1, 1994SaveLearn
Speech Dialogue with Facial Displays: Multimodal Human-Computer ConversationHuman face-to-face conversation is an ideal model for human-computer dialogue. One of the major features of face-to-face communication is its multiplicity of communication channels that act on…Katashi Nagao, Akikazu Takeuchi·Jun 1, 1994SaveLearn
Intentions and Information in DiscourseThis paper is about the flow of inference between communicative intentions, discourse structure and the domain during discourse processing. We augment a theory of discourse interpretation with a…Nicholas Asher, Alex Lascarides·Jun 1, 1994SaveLearn
Extracting Noun Phrases from Large-Scale Texts: A Hybrid Approach and Its Automatic EvaluationTo acquire noun phrases from running texts is useful for many applications, such as word grouping,terminology indexing, etc. The reported literatures adopt pure probabilistic approach, or pure…Kuang-hua Chen, Hsin-Hsi Chen·Jun 1, 1994SaveLearn
Dual-Coding Theory and Connectionist Lexical SelectionWe introduce the bilingual dual-coding theory as a model for bilingual mental representation. Based on this model, lexical selection neural networks are implemented for a connectionist transfer…Ye-Yi Wang·May 31, 1994SaveLearn