An Empirically Based System for Processing Definite Descriptions
Computational LinguisticsPublished 1 December 2000Open access
Renata Vieira, Massimo Poesio
Citations198
SJR quartileQ1
SJR score1.15
SNIP4.16
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
The annotated corpus was used to extensively evaluate the proposed techniques for matching definite descriptions with their antecedents, discourse segmentation, recognizing discourse-new descriptions, and suggesting anchors for bridging descriptions.
Abstract
We present an implemented system for processing definite descriptions in arbitrary domains. The design of the system is based on the results of a corpus analysis previously reported, which highlighted the prevalence of discourse-new descriptions in newspaper corpora. The annotated corpus was used to extensively evaluate the proposed techniques for matching definite descriptions with their antecedents, discourse segmentation, recognizing discourse-new descriptions, and suggesting anchors for bridging descriptions.
Keywords
Computer Science
BiometricsThe Measurement of Observer Agreement for Categorical Data
78,934 Citations1977J. Richard Landis, Gary G. Koch
A general statistical methodology for the analysis of multivariate categorical data arising from observer reliability studies is presented and tests for interobserver bias are presented in terms of first-order marginal homogeneity and measures of interob server agreement are developed as generalized kappa-type statistics.
Revue économiqueNonparametric Statistics for the Behavioral Sciences
35,492 Citations1958Henri Guitton, Sidney Siegel
Journal of the American Statistical AssociationContent Analysis: An Introduction to its Methodology.
24,566 Citations1984Mack Shelley, Klaus Krippendorff
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.
Language<b>WordNet: An electronic lexical database</b> . Ed. by Christiane Fellbaum. Cambridge, MA: MIT Press, 1998. Pp. xxii, 423.
11,687 Citations2000Adam Kilgarriff
The lexical database: nouns in WordNet, George A. Miller modifiers in WordNet, Katherine J. Miller a semantic network of English verbs, and applications of WordNet: building semantic concordances are presented.
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
Scholarworks (University of Massachusetts Amherst)The Semantics of Definite and Indefinite Noun Phrases
3,012 Citations1982Irene Heim
Computational LinguisticsAttention, intentions, and the structure of discourse
2,606 Citations1986Barbara J. Grosz, Candace L. Sidner
A new theory of discourse structure that stresses the role of purpose and processing in discourse is explored and various properties of discourse are described, and explanations for the behavior of cue phrases, referring expressions, and interruptions are explored.
arXiv (Cornell University)Assessing agreement on classification tasks: the kappa statistic
2,092 Citations1996Jean Carletta
Centering: A Framework for Modelling the Local Coherence of Discourse,
1,785 Citations1995Barbara J. Grosz, Aravind K. Joshi +1 more
Interactions between local coherence and choice of referring expressions are examined; it is argued that differences in coherence correspond in part to the inference demands made by different types of referring expressions, given a particular attentional state.
TextTiling: segmenting text into multi-paragraph subtopic passages
1,253 Citations1997Marti A. Hearst
The algorithm is fully implemented and is shown to produce segmentation that corresponds well to human judgments of the subtopic boundaries of 12 texts, which should be useful for many text analysis tasks, including information retrieval and summarization.
Computational linguistics in 1990
1,247 Citations1990Hans Karlgren
Computational linguistics is what the authors make it, and the concept also evolves with each of us in the vague, successive way in which other words in human language so fruitfully keep changing.
Studies in linguistics and philosophyParsing By Chunks
878 Citations1991Steven Abney
The typical chunk consists of a single content word surrounded by a constellation of function words, matching a fixed template, and the relationships between chunks are mediated more by lexical selection than by rigid templates.
Wiley Encyclopedia of Electrical and Electronics EngineeringComputational Linguistics
834 Citations1999Fred Popowich
Computational LinguisticsAn algorithm for pronominal anaphora resolution
758 Citations1994Shalom Lappin, Herbert J. Leass
The algorithm applies to the syntactic representations generated by McCord's Slot Grammar parser and relies on salience measures derived from syntactic structure and a simple dynamic model of attentional state and to models of anaphora resolution that invoke a variety of informational factors in ranking antecedent candidates.
A model-theoretic coreference scoring scheme
682 Citations1995Marc Vilain, John D. Burger +3 more
This note describes a scoring scheme for the coreference task in MUC6 that improves on the original approach by grounding the scoring scheme in terms of a model; producing more intuitive recall and precision scores; and not requiring explicit computation of the transitive closure of coreference.
Linguistics and PhilosophyTemporal interpretation, discourse relations and commonsense entailment
636 Citations1993Alex Lascarides, Nicholas Asher
This paper presents a formal account of how to determine the discourse relations between propositions introduced in a text, and the relations between the events they describe.
Providing a unified account of definite noun phrases in discourse
438 Citations1983Barbara J. Grosz, Aravind K. Joshi +1 more
A unified account of definite noun phrases in discourse is provided and a description of the construction of sentences using these phrases and their meanings is provided.
Named Entity recognition without gazetteers
431 Citations1999Andrei Mikheev, Marc Moens +1 more
It is shown that, for the text type and task of this competition, it is sufficient to use relatively small gazetteers of well-known names, rather than large gazetters of low-frequency names.
University of California, Berkeley eBooksThe representation and use of focus in dialogue understanding.
424 Citations1977Barbara J. Grosz
The ability to represent focus of attention in a languageunderstanding system results in a new approach to an important problemin discourse comprehension -- the identification of the referents ofdefinite noun phrases.
Computational LinguisticsThe reliability of a dialogue structure coding scheme
401 Citations1997Jean Carletta, Stephen Isard +4 more
This paper describes the reliability of a dialogue structure coding scheme based on utterance function, game structure, and higher-level transaction structure that has been applied to a corpus of spontaneous task-oriented spoken dialogues.
A Formal Approach to Discourse Anaphora
378 Citations2016Bonnie Webber
The view is that dealing with anaphoric language can be decomposed into two complementary tasks: identifying what a text potentially makes available for anaphor reference and how it does so and constraining the candidate set of a given anaphic expression down to one possible choice.
Language<b>The Core Language Engine</b> . Ed. by Hiyan Alshawi. (A Bradford book.) Cambridge, MA: The MIT Press, 1992. Pp. xviii, 322. $37.50.
350 Citations1994Michael A. Covington
Introduction to the CLE, Hiyan Alshawi and Robert C. Moore - language analysis and interpretation, overview of CLE components logical forms, and levels of logical form in the CLE.
Text, speech and language technologyA Preferential, Pattern-Seeking, Semantics for Natural Language Inference
337 Citations2007Yorick Wilks
Artificial IntelligenceA preferential, pattern-seeking, Semantics for natural language inference
329 Citations1975Yorick Wilks
The way in which a Preference Semantics system for natural language analysis and generation tackles a difficult class of anaphoric inference problems: those requiring either analytic knowledge of a complex sort, or requiring weak inductive knowledge of the course of events in the real world.
arXiv (Cornell University)A Corpus-Based Investigation of Definite Description Use
322 Citations1997Massimo Poesio, Renata Vieira
DSpace@MIT (Massachusetts Institute of Technology)Towards a Computational Theory of Definite Anaphora Comprehension in English Discourse
292 Citations1979Candace L. Sidner
The focussing mechanism is designed to take advantage of syntactic and semantic information encoded as constraints on the choice of anaphora interpretation, and provides a principled means for choosing when to apply the constraints in the comprehension process.
LanguageA pragmatic analysis of so-called anaphoric islands
207 Citations1991Gregory Ward, Richard Sproat +1 more
Disambiguation of proper names in text
182 Citations1997Nina Wacholder, Yael Ravin +1 more
The types of ambiguity that make the discovery of proper names difficult in text are analyzed, and the heuristics used to disambiguate names in Nominator, a fully-implemented module for proper name recognition developed at the IBM T. J. Watson Research Center are described.
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.
University of Sheffield
165 Citations1995Robert Gaizauskas, Kevin Humphreys +2 more
The LaSIE (Large Scale Information Extraction) system has been developed at the University of Sheffield as part of an ongoing research effort into information extraction and, more generally, natural language engineering.
Journal of SemanticsDefiniteness and the Processing of Noun Phrases in Natural Discourse
161 Citations1990Kari Fraurud
This paper argues for a more complex picture of the role of definiteness in the processing of NPs, and presents a corpus-based study of the co-referential properties of definite and indefinite NPs in natural, unrestricted texts.
Overview of MUC-7/MET-2
159 Citations1998Nancy Chinchor
The tasks performed by the systems participating in the seventh Message Understanding Conference and the Second Multilingual Entity Task are described here in general terms with examples.
SRI International FASTUS system
136 Citations1995Douglas E. Appelt, Jerry R. Hobbs +6 more
SRI International participated in the MUC-6 evaluation using the latest version of SRI's FASTUS system, an architecture consisting of cascaded finite state transducers each providing an additional level of analysis of the input, together with merging of the final results.
Overview of results of the MUC-6 evaluation
127 Citations1995Beth Sundheim
The latest in a series of natural language processing system evaluations, the MUC-6 evaluation entailed Named Entity and Coreference tasks entailed Standard Generalized Markup Language (SGML) annotation of texts and were being conducted for the first time.
Internal and external evidence in the identification and semantic categorization of proper names
123 Citations1996David D. McDonald
The proper name recognition and classification facility ("PNV") of the SPARSER natural language understanding system has been described and has been used very successfully in the analysis of unrestricted texts in several sublanguages taken from online news sources.
Towards the automatic identification of adjectival scales
117 Citations1993Vasileios Hatzivassiloglou, Kathleen McKeown
This paper presents a method to group adjectives according to their meaning, as a first step towards the automatic identification of adjectival scales, and shows how a clustering algorithm can use similarities to produce the groups of adjectives.
Anaphora resolution
113 Citations1988Jaime Carbonell, Ralf D. Brown
This paper examines the hypothesis that instead of attempting to construct a monolithic method for resolving anaphora, the combination of multiple strategies, each exploiting a different knowledge source, proves more effective - theoretically and computationally.
Choice Reviews OnlineCorpus processing for lexical acquisition
106 Citations1997
Part 1 Introduction: issues in text-based lexicon acquistion - the problem of lexical knowledge Acquistion text- based lexicon acquisition, Branimir Boguraev, James Pustejovsky.
Resolving bridging references in unrestricted text
90 Citations1997Massimo Poesio, Renata Vieira +1 more
The latest version of this system, which handles some types of bridging references, uses WordNet as a source of lexical knowledge, and achieves a recall of 65% is presented.
A decision-based approach to rhetorical parsing
80 Citations1999Daniel Marcu
A shift-reduce rhetorical parsing algorithm that learns to construct rhetorical structures of texts from a corpus of discourse-parse action sequences that exploits robust lexical, syntactic, and semantic knowledge sources.
A statistical profile of the Named Entity task
76 Citations1997David D. Palmer, David Day
Using the results of the statistical analysis, an algorithm for lower bound estimation for Named Entity corpora is proposed and the significance of the cross-lingual comparisons provided by the analysis is discussed.
Language<b>Memory and context for language interpretation.</b> By Hiyan Alshawi. (Studies in Natural Language Processing.) Cambridge: Cambridge University Press, 1987. Pp. ix, 188.
73 Citations1989Rong Chen
This paper presents the mechanisms of the Capture system, a system for performing database capture and its applications, and some of the techniques used for efficient retrieval.
Corpus-based identification of non-anaphoric noun phrases
66 Citations1999David L. Bean, Ellen Riloff
A corpus-based algorithm is developed for automatically identifying definite noun phrases that are non-anaphoric, which has the potential to improve the efficiency and accuracy of coreference resolution systems.
Resolving Quasi Logical Forms
64 Citations1990Hiyan Alshawi
Analysis of syntax-based pronoun resolution methods
51 Citations1999Joel Tetreault
A pronoun resolution algorithm that adheres to the constraints and rules of Centering Theory and is an alternative to Brennan et al.'s 1987 algorithm, the Left-Right Centering Algorithm (LRC), which is compared with three other pronoun resolution methods.
Recognizing referential links
48 Citations1997Megumi Kameyama
An efficient and robust reference resolution algorithm in an end-to-end state-of-the-art information extraction system, which must work with a considerably impoverished syntactic analysis of the input sentences.
RAFT/RAPR and centering: a comparison and discussion of problems related to processing complex sentences
47 Citations1994Linda Z. Suri, Kathleen F. McCoy
As a result of (some) differences between the frameworks with respect to these preferences, resolvhlg a pronoun to have the same grammatical role as its antecedent is less important in centering than it is in RAFT/RAPR (Section 4.3).
Categorizing and standardizing proper nouns for efficient information retrieval
39 Citations1996Woojin Paik, Elizabeth D. Liddy +2 more
The most recent implementation and evaluation of the proper noun categorization and standardization module of the DRLINK document detection system being developed at Syracuse University, under the auspices of ARPA's TIPSTER program is described.
An empirical approach to VP ellipsis
38 Citations1997Daniel Hardt
Evaluating a focus-based approach to anaphora resolution
30 Citations1998Saliha Azzam, Kevin Humphreys +1 more
An approach to anaphora resolution based on a focusing algorithm, and implemented within an existing MUC (Message Understanding Conference) Information Extraction system, allowing quantitative evaluation against a substantial corpus of annotated real-world texts.
Studies in corpus linguisticsProcessing definite descriptions in corpora
29 Citations2000Renata Vieira, Massimo Poesio
An algorithm which resolves anaphoric definite descriptions and also identifies novel ones is proposed and evaluated by comparing its results with an annotation produced by human subjects.
ERADetecting Subject Boundaries Within Text: A Language Independent Statistical Approach
24 Citations1997Korin Richmond, A. J. Smith +1 more
An algorithm for detecting subject boundaries within text based on a statistical lexical similarity measure is described, which is a robust and reliable algorithm which exhibits improved accuracy without sacrificing language independency and improves accuracy and reliability.
Towards resolution of bridging descriptions
22 Citations1997Renata Vieira, Simone Teufel
Analysis of a collection of 20 Wall Street Journal articles from the Penn Treebank Corpus and experiments with WordNet to identify relations between bridging descriptions and their antecedents are reported.
Bridging textual ellipses
21 Citations1996Udo Hahn, Michael Strube +1 more
A hybrid text understanding methodology for the resolution of textual ellipsis that integrates language-independent conceptual criteria and language-dependent functional constraints is presented.
Statistical significance of MUC-6 results
21 Citations1995Nancy Chinchor
The results of the statistical testing for the three MUC-6 tasks where a single metric could be associated with a system's performance are given.
Long distance pronominalisation and global focus
20 Citations1998Janet Hitzeman, Massimo Poesio
It is concluded that a discourse focus stack mechanism of the type proposed by Sidner is essential to account for the use of these referring expressions and is suggested to be revising the Grosz & Sidner framework by allowing for the possibility that an entity in a focus space may have special status.
Lexical Clustering and Definite Description Interpretation
20 Citations1998Massimo Poesio, Sabine Schulte +2 more
It is found that the choice of parameters has a clear effect, and that the best results are obtained by measuring the distance between lexical vectors using the cosine measure, while factors other than semantic distance play the main role in the majority of cases.
Probabilistic Resolution of Anaphoric Reference
12 Citations1992John D. Burger, Dennis Connolly
By adopting a Bayesian approach, this paper is able to combine diverse evidence in a principled way, extend current understanding of linguistic phenomena by quantifying relationships empirically, and better model the non-deterministic role of linguistic evidence in resolution of anaphora.
Language Resources and EvaluationTowards More Comprehensive Evaluation in Anaphora Resolution
11 Citations2000Ruslan Mitkov
Using a Bayesian Framework to Identify the Referents of Definite Descriptions
4 Citations1992Sehyeong Cho, Dae Dug
This paper describes a principled method for weighing evidence from various sources in order to identify the referent of a description that is not guaranteed to be correct and adopts assumptions consistent with Gricean maxims of conversation, thereby mapping the problem into a simple Bayesian framework.