Knowledge Representation for Lexical Semantics: Is Standard First Order Logic Enough?Natural language understanding applications such as interactive planning and face-to-face translation require extensive inferencing. Many of these inferences are based on the meaning of particular…Marc Light, Lenhart Schubert·Dec 10, 1994SaveLearn
An Extended Clustering Algorithm for Statistical Language ModelsStatistical language models frequently suffer from a lack of training data. This problem can be alleviated by clustering, because it reduces the number of free parameters that need to be trained.…Joerg P. Ueberla·Dec 6, 1994SaveLearn
N-Gram Cluster Identification During Empirical Knowledge Representation GenerationThis paper presents an overview of current research concerning knowledge extraction from technical texts. In particular, the use of empirical techniques during the identification and generation of a…Robin Collier·Dec 5, 1994SaveLearn
Dependency Grammar and the Parsing of Chinese SentencesDependency Grammar has been used by linguists as the basis of the syntactic components of their grammar formalisms. It has also been used in natural language parsing. In China, attempts have been…Bong Yeung Tom Lai, Changning Huang·Dec 1, 1994SaveLearn
Has a Consensus NL Generation Architecture Appeared, and is it Psycholinguistically Plausible?I survey some recent applications-oriented NL generation systems, and claim that despite very different theoretical backgrounds, these systems have a remarkably similar architecture in terms of the…Ehud Reiter·Nov 30, 1994SaveLearn
Automatic Generation of Technical DocumentationNatural-language generation (NLG) techniques can be used to automatically produce technical documentation from a domain knowledge base and linguistic and contextual models. We discuss this…Ehud Reiter, Chris Mellish, John Levine·Nov 29, 1994SaveLearn
Complexity of Scrambling: A New Twist to the Competence - Performance DistinctionIn this paper we discuss the following issue: How do we decide whether a certain property of language is a competence property or a performance property? Our claim is that the answer to this question…Aravind K Joshi·Nov 29, 1994SaveLearn
An Efficient Probabilistic Context-Free Parsing Algorithm that Computes Prefix ProbabilitiesWe describe an extension of Earley's parser for stochastic context-free grammars that computes the following quantities given a stochastic context-free grammar and an input string: a)…Andreas Stolcke·Nov 28, 1994SaveLearn
The Speech-Language Interface in the Spoken Language TranslatorThe Spoken Language Translator is a prototype for practically useful systems capable of translating continuous spoken language within restricted domains. The prototype system translates air travel…David Carter, Manny Rayner·Nov 23, 1994SaveLearn
Classifier Assignment by Corpus-based ApproachThis paper presents an algorithm for selecting an appropriate classifier word for a noun. In Thai language, it frequently happens that there is fluctuation in the choice of classifier for a given…Virach Sornlertlamvanich, Wantanee Pantachat, Surapant Meknavin·Nov 21, 1994SaveLearn
Manipulating Human-oriented Dictionaries with very simple toolsThis paper presents a methodology for building and manipulating human-oriented dictionaries. This methodology has been applied in the construction of a French-English-Malay dictionary which has been…Jean Gaschler, Mathieu Lafourcade·Nov 18, 1994SaveLearn
Multi-Dimensional InheritanceIn this paper, we present an alternative approach to multiple inheritance for typed feature structures. In our approach, a feature structure can be associated with several types coming from different…Gregor Erbach·Nov 17, 1994SaveLearn
Reverse Queries in DATRDATR is a declarative representation language for lexical information and as such, in principle, neutral with respect to particular processing strategies. Previous DATR compiler/interpreter systems…Hagen Langer·Nov 17, 1994SaveLearn
Abstract Generation based on Rhetorical Structure ExtractionWe have developed an automatic abstract generation system for Japanese expository writings based on rhetorical structure extraction. The system first extracts the rhetorical structure, the compound…Kenji Ono, Kazuo Sumita, Seiji Miike Research et al.·Nov 17, 1994SaveLearn
Adaptive Sentence Boundary DisambiguationLabeling of sentence boundaries is a necessary prerequisite for many natural language processing tasks, including part-of-speech tagging and sentence alignment. End-of-sentence punctuation marks are…David D. Palmer, Marti A. Hearst·Nov 16, 1994SaveLearn
Free-ordered CUG on Chemical Abstract MachineWe propose a paradigm for concurrent natural language generation. In order to represent grammar rules distributively, we adopt categorial unification grammar (CUG) where each category owns its…Satoshi Tojo·Nov 16, 1994SaveLearn
Extraction in Dutch with Lexical RulesUnbounded dependencies are often modelled by ``traces'' (and ``gap threading'') in unification-based grammars. Pollard and Sag, however, suggest an analysis of extraction based on…Gerrit Rentier·Nov 14, 1994SaveLearn
Focus on ``only" and ``Not"Krifka [1993] has suggested that focus should be seen as a means of providing material for a range of semantic and pragmatic functions to work on, rather than as a specific semantic or pragmatic…Allan Ramsay·Nov 11, 1994SaveLearn
Interlanguage Signs and Lexical Transfer ErrorsA theory of interlanguage (IL) lexicons is outlined, with emphasis on IL lexical entries, based on the HPSG notion of lexical sign. This theory accounts for idiosyncratic or lexical transfer of…Atle Ro·Nov 11, 1994SaveLearn
Comlex Syntax: Building a Computational LexiconWe describe the design of Comlex Syntax, a computational lexicon providing detailed syntactic information for approximately 38,000 English headwords. We consider the types of errors which arise in…Ralph Grishman, Catherine Macleod, Adam Meyers·Nov 10, 1994SaveLearn
Extending DRT with a Focusing Mechanism for Pronominal Anaphora and Ellipsis ResolutionCormack (1992) proposed a framework for pronominal anaphora resolution. Her proposal integrates focusing theory (Sidner et al.) and DRT (Kamp and Reyle). We analyzed this methodology and adjusted it…Jose Abracos, Jose Gabriel Lopes·Nov 9, 1994SaveLearn
Parsing Using Linearly Ordered Phonological RulesA generate and test algorithm is described which parses a surface form into one or more lexical entries using linearly ordered phonological rules. This algorithm avoids the exponential expansion of…Michael Maxwell·Nov 8, 1994SaveLearn
Automatically Identifying Morphological Relations in = Machine-Readable DictionariesWe describe an automated method for identifying classes of morphologically related words in an on-line dictionary, and for linking individual senses in the derived form to one or more senses in the…Joseph Pentheroudakis, Lucy Vanderwende, Microsoft Corporation·Nov 8, 1994SaveLearn
Phoneme-level speech and natural language intergration for agglutinative languagesA new tightly coupled speech and natural language integration model is presented for a TDNN-based large vocabulary continuous speech recognition system. Unlike the popular n-best techniques developed…Geunbae Lee Jong-Hyeok Lee Kyunghee Kim·Nov 5, 1994SaveLearn
From Regular to Context Free to Mildly Context Sensitive Tree Rewriting Systems: The Path of Child Language AcquisitionCurrent syntactic theory limits the range of grammatical variation so severely that the logical problem of grammar learning is trivial. Yet, children exhibit characteristic stages in syntactic…Robert Frank·Nov 4, 1994SaveLearn