Learning parse and translation decisions from examples with rich context
Published 1 January 1997Open access
Ulf Hermjakob, Raymond J. Mooney
Citations60
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
A knowledge and context-based system for parsing and translating natural language and evaluate it on sentences from the Wall Street Journal, which relies heavily on context, as encoded in features which describe the morphological, syntactic, semantic and other aspects of a given parse state.
Abstract
We present a knowledge and context-based system for parsing and translating natural language and evaluate it on sentences from the Wall Street Journal. Applying machine learning techniques, the system uses parse action examples acquired under supervision to generate a deterministic shift-reduce parser in the form of a decision structure. It relies heavily on context, as encoded in features which describe the morphological, syntactic, semantic and other aspects of a given parse state.
Keywords
Computer Science
C4.5: Programs for Machine Learning
23,665 Citations1992J. R. Quinlan
A complete guide to the C4.5 system as implemented in C for the UNIX environment, which starts from simple core learning methods and shows how they can be elaborated and extended to deal with typical problems such as missing data and over hitting.
Machine LearningInduction of Decision Trees
14,815 Citations1986J. R. Quinlan
This paper summarizes an approach to synthesizing decision trees that has been used in a variety of systems, and it describes one such system, ID3, in detail, which is described in detail.
Machine LearningInduction of decision trees
12,383 Citations1986J. R. Quinlan
This paper summarizes an approach to synthesizing decision trees that has been used in a variety of systems, and it describes one such system, ID3, in detail, which is described in detail.
Building a Large Annotated Corpus of English: The Penn Treebank
7,528 Citations1993Mitchell P. Marcus
College Composition and CommunicationA Comprehensive Grammar of the English Language
5,535 Citations1987P Beauvais, Randolph Quirk +3 more
The Philosophical ReviewGeneralized Phrase Structure Grammar.
1,843 Citations1989Scott Soames, Gerald Gazdar +3 more
"Generalized Phrase Structure Grammar" provides the definitive exposition of the theory of grammar originally proposed by Gerald Gazdar and developed during half a dozen years' work with his colleagues Ewan Klein, Geoffrey Pullum, and Ivan Sag.
A statistical approach to machine translation
1,699 Citations1990Peter F. Brown, John Cocke +6 more
The application of the statistical approach to translation from French to English and preliminary results are described and the results are given.
Transformation-based error-driven learning and natural language processing: a case study in part-of-speech tagging
1,531 Citations1995Eric Brill
This paper describes a simple rule-based approach to automated learning of linguistic knowledge that has been shown for a number of tasks to capture information in a clearer and more direct fashion without a compromise in performance.
Artificial IntelligenceDefinite clause grammars for language analysis—A survey of the formalism and a comparison with augmented transition networks
985 Citations1980Fernando C. N. Pereira, David H. Warren
It is argued that DCGs can be at least as efficient as ATNs, whilst the DCG formalism is clearer, more concise and in practice more powerful.
Language<b>A theory of syntactic recognition for natural language</b> . By Mitchell P. Marcus. Cambridge, MA: MIT Press, 1980. Pp. 335. $25.00.
919 Citations1982Michael B. Kac
It will be shown that this 'determinism' hypothesis, explored within the context of the grammar of English, leads to a simple mechanism, a grammar interpreter.
Machine LearningLearning Decision Lists
761 Citations1987Ronald L. Rivest
This paper introduces a new representation for Boolean functions, called decision lists, and shows that they are efficiently learnable from examples, and strictly increases the set of functions known to be polynomially learnable, in the sense of Valiant (1984).
A new statistical parser based on bigram lexical dependencies
619 Citations1996Michael Collins
A new statistical parser which is based on probabilities of dependencies between head-words in the parse tree, which trains on 40,000 sentences in under 15 minutes and can be improved to over 200 sentences a minute with negligible loss in accuracy.
Cambridge University Press eBooksTree adjoining grammars: How much context-sensitivity is required to provide reasonable structural descriptions?
550 Citations1985Aravind K. Joshi
Statistical decision-tree models for parsing
533 Citations1995David M. Magerman
SPATTER is described, a statistical parser based on decision-tree learning techniques which constructs a complete parse for every sentence and achieves accuracy rates far better than any published result.
Columbia Academic Commons (Columbia University)Translating Collocations for Bilingual Lexicons: A Statistical Approach
497 Citations1996Frank Smadja, Kathleen McKeown +1 more
A program named Champollion is described which, given a pair of parallel corpora in two different languages and a list of collocations in one of them, automatically produces their translations, to provide a tool for compiling bilingual lexical information above the word level in multiple languages, for different domains.
Generating production rules from decision trees
474 Citations1987J. R. Quinlan
This paper describes a technique for transforming such trees to small sets of production rules, a common formalism for expressing knowledge in expert systems, and provides a way of combining different decision trees for the same classification domain.
Language<b>Introduction to the theory of grammar</b> . By Hank van Riemsdijk and Edwin Williams. Cambridge, MA: MIT Press. Pp. xvi, 366. $35.00.
432 Citations1989John Goldsmith
Integrating multiple knowledge sources to disambiguate word sense
410 Citations1996Hwee Tou Ng, Hian Beng Lee
This approach integrates a diverse set of knowledge sources to disambiguate word sense, including part of speech of neighboring words, morphological form, the unordered set of surrounding words, local collocations, and verb-object syntactic relation.
Efficient Parsing for Natural Language
403 Citations1986Masaru Tomita
Decision lists for lexical ambiguity resolution
362 Citations1994David Yarowsky
This paper presents a statistical decision procedure for lexical ambiguity resolution that exploits both local syntactic patterns and more distant collocational evidence, generating an efficient, effective, and highly perspicuous recipe for resolving a given ambiguity.
Machine LearningLearning decision lists
355 Citations1987Ronald L. Rivest
This paper introduces a new representation for Boolean functions, called decision lists, and shows that they are efficiently learnable from examples, and strictly increases the set of functions known to be polynomially learnable, in the sense of Valiant (1984).
Text-translation alignment
342 Citations1993Martin Kay, Martin Röscheisen
Coping with ambiguity and unknown words through probabilistic models
261 Citations1993Ralph Weischedel, Richard Schwartz +3 more
arXiv (Cornell University)MBT: A Memory-Based Part of Speech Tagger-Generator
259 Citations1996Walter Daelemans, Jakub Zavrel +2 more
A program for aligning sentences in bilingual corpora
258 Citations1991William A. Gale, Kenneth Church
A method for aligning sentences in parallel texts, such as the Canadian Hansards, based on a simple statistical model of character lengths is described, developed and tested on a small trilingual sample of Swiss economic reports.
Automatic acquisition of a large subcategorization dictionary from corpora
206 Citations1993Christopher D. Manning
It is shown that statistical filtering of the results of a finite state parser running on the output of a stochastic tagger produces high quality results, despite the error rates of the tagger and the parser.
arXiv (Cornell University)Comparative Experiments on Disambiguating Word Senses: An Illustration of the Role of Bias in Machine Learning
195 Citations1996Raymond J. Mooney
Evaluating automated and manual acquisition of anaphora resolution strategies
176 Citations1995Chinatsu Aone, Scott Bennett
This work uses Japanese newspaper articles tagged with discourse information as training examples for a machine learning algorithm which employs the C4.5 decision tree algorithm by Quinlan (Quinlan, 1993) to build an automatically trainable anaphora resolution system.
Cambridge University Press eBooksParsing in functional unification grammar
173 Citations1985Martin Kay
Towards history-based grammars
145 Citations1993Ezra Black, Fred Jelinek +4 more
HBG incorporates lexical, syntactic, semantic, and structural information from the parse tree into the disambiguation process in a novel way and significantly outperforms P-CFG, increasing the parsing accuracy rate from 60% to 75%, a 37% reduction in error.
Elsevier eBooksEye Movements and Spoken Language Comprehension
141 Citations2006Michael K. Tanenhaus, John C. Trueswell
Eye movements are a response measure of choice for studies addressing many classical questions in psycholinguistics, e.g., is the processing of stop consonants categorical; does context influence the earliest moments of temporary lexical and syntactic ambiguity resolution.
The Candide system for machine translation
140 Citations1994Adam Berger, Peter F. Brown +7 more
An overview of Candide, a system for automatic translation of French text to English text, which uses methods of information theory and statistics to develop a probability model of the translation process to generate English translations of previously unseen French sentences.
Parsing algorithms and metrics
139 Citations1996Joshua Goodman
Two new algorithms are presented: the "Labelled Recall Algorithm," which maximizes the expected Labelled Recall Rate, and the "Bracketed Recall Al algorithm", which maximized the Bracketed recall Rate.
Artificial IntelligenceAn empirical study of automated dictionary construction for information extraction in three domains
136 Citations1996Ellen Riloff
The performance of AutoSlog across the three domains is compared, the lessons learned about the generality of this approach are discussed, and results from two experiments which demonstrate that novice users can generate effective dictionaries using autoSlog are presented.
Machine Translation: A Knowledge-Based Approach
130 Citations1992Sergei Nirenburg, Jaime Carbonell +2 more
The authors introduce the general paradigm of knowledge-based MT, survey major recent developments, compare it with other approaches and present a paradigmatic view of its component processes-natural language analysis, natural language generation, text meaning representation, ontological modeling, etc.
LinguaMachine translation: Theoretical and methodological issues
103 Citations1989
The authors introduce the general paradigm of knowledge-based MT, survey major recent developments, compare it with other approaches and present a paradigmatic view of its component processes.
Language<b>A course in GB syntax</b> : Lectures on binding and empty categories. By Howard Lasnik and Juan Uriagereka. (Current studies in linguistics series.) Cambridge, MA: MIT Press, 1988. Pp. xii, 178.
91 Citations1990Ann Farmer
A Course in GB Syntax is a new kind of linguistics textbook that presents the fundamental concepts of the Government-Binding approach to syntax in a lecture-dialogue format that conveys the sense of a changing field, with live issues under debate.
Development and evaluation of a broad-coverage probabilistic grammar of English-language computer manuals
88 Citations1992Ezra Black, John Lafferty +1 more
An approach to grammar development where the task is decomposed into two separate subtasks, with the goal of producing a set of rules that have a large coverage on a blind test set of sentences.
Journal of Artificial Intelligence ResearchCue Phrase Classification Using Machine Learning
69 Citations1996Diane Litman
This paper explores the use of machine learning for classifying cue phrases as discourse or sentential in natural language processing systems that exploit discourse structure, e.g., for performing tasks such as anaphora resolution and plan recognition.
Machine TranslationLarge-scale automatic extraction of an English-Chinese translation lexicon
63 Citations1995Dekai Wu, Xuanyin Xia
This work introduces a fully automatic two-stage statistical methodology that is able to learn translations for collocations and reports experimental results on automatic extraction of an English-Chinese translation lexicon, by statistical analysis of a large parallel corpus.
Using inductive logic programming to automate the construction of natural language parsers
36 Citations1996John M. Zelle
Results support the claim that ILP techniques as implemented in C scHILL represent a viable alternative with significant potential advantages over neural-network, propositional, and probabilistic approaches to empirical parser construction.
Publications of the UdS (Saarland University)SCREEN : learning a flat syntactic and semantic spoken language analysis using artificial neural networks
32 Citations1997Stefan Wermter, Volker Weber
The acquisition and use of context-dependent grammars for English
31 Citations1992Robert F. Simmons, Yeong-Ho Yu
It is concluded that CDG is a computationally and conceptually tractable approach for the construction of sentence grammar for large subsets of natural language text.
Machine TranslationCurrent research in Machine Translation
26 Citations1993Harold Somers
Alternative approaches discussed are systems which develop or update their grammars semi-automatically, dialogue MT, and corpus-based MT including example-based and statistical approaches.
Automating Feature Set Selection for Case-Based Learning of Linguistic Knowledge
25 Citations1996Claire Cardie
The linguistic bias approach to feature set selection offers new possibilities for case-based learning of natural language: it simplifies the process of instance representation design and, in theory, obviates the need for separate instance representations for each linguistic knowledge acquisition task.
ArXiv.orgEmergent Linguistic Rules from Inducing Decision Trees: Disambiguating Discourse Clue Words
24 Citations1994Eric V. Siegel, Kathleen McKeown
This work applies decision tree induction to the problem of discourse clue word sense disambiguation and finds that the automatic partitioning of the training set which is intrinsic to decision Tree induction gives rise to linguistically viable rules.
Learning parse and translation decisions from examples with rich context
20 Citations1997Ulf Hermjakob, Raymond J. Mooney
Learning to disambiguate relative pronouns
20 Citations1992Claire Cardie
This paper uses a well-known conceptual clustering system to create a case-based memory that predicts the antecedent of a wh-word given a description of the clause that precedes it and believes that the technique provides a general approach for the automated acquisition of additional disambiguation heuristics for natural language systems, especially for problems that require the assimilation of syntactic and semantic knowledge.