Eugene Charniak - Academia.edu (original) (raw)
Papers by Eugene Charniak
Meeting of the Association for Computational Linguistics, 2010
We investigate coreference relationships between NPs with the same head noun. It is relatively co... more We investigate coreference relationships between NPs with the same head noun. It is relatively common in unsupervised work to assume that such pairs are coreferent- but this is not always true, es- pecially if realistic mention detection is used. We describe the distribution of non- coreferent same-head pairs in news text, and present an unsupervised generative model which learns not
North American Chapter of the Association for Computational Linguistics, 2009
We describe a generative model for clustering named entities which also models named en- tity int... more We describe a generative model for clustering named entities which also models named en- tity internal structure, clustering related words by role. The model is entirely unsupervised; it uses features from the named entity itself and its syntactic context, and coreference in- formation from an unsupervised pronoun re- solver. The model scores 86% on the MUC-7 named-entity dataset. To our
Meeting of the Association for Computational Linguistics, 2008
Research on coreference resolution and sum- marization has modeled the way entities are realized ... more Research on coreference resolution and sum- marization has modeled the way entities are realized as concrete phrases in discourse. In particular there exist models of the noun phrase syntax used for discourse-new versus discourse-old referents, and models describ- ing the likely distance between a pronoun and its antecedent. However, models of discourse coherence, as applied to information ordering tasks, have
Conference of the European Chapter of the Association for Computational Linguistics, 2009
We present an algorithm for pronoun- anaphora (in English) that uses Expecta- tion Maximization (... more We present an algorithm for pronoun- anaphora (in English) that uses Expecta- tion Maximization (EM) to learn virtually all of its parameters in an unsupervised fashion. While EM frequently fails to find good models for the tasks to which it is set, in this case it works quite well. We have compared it to several systems avail- able on the
Meeting of the Association for Computational Linguistics, 2008
When multiple conversations occur simultane- ously, a listener must decide which conversa- tion e... more When multiple conversations occur simultane- ously, a listener must decide which conversa- tion each utterance is part of in order to inter- pret and respond to it appropriately. We refer to this task as disentanglement. We present a corpus of Internet Relay Chat (IRC) dialogue in which the various conversations have been manually disentangled, and evaluate annota- tor reliability. This
National Conference on Artificial Intelligence, 1991
Plan-recognition requires the construction of possible plans which could explain a set of observe... more Plan-recognition requires the construction of possible plans which could explain a set of observed actions, and then selecting one or more of them as providing the best explanation. In this paper we present a formal model of the latter process based upon probability theory. Our model ...
Meeting of the Association for Computational Linguistics, 1999
We present a method for extracting parts of objects from wholes (e.g. "speedometer" fro... more We present a method for extracting parts of objects from wholes (e.g. "speedometer" from "car"). Given a very large corpus our method finds part words with 55% accuracy for the top 50 words as ranked by the system. The part list could be scanned by an end-user and added to an existing ontology (such as WordNet), or used as a
Proceedings of the 46th Annual Meeting of the Association for Computational Linguistics on Human Language Technologies Short Papers - HLT '08, 2008
Research on coreference resolution and summarization has modeled the way entities are realized as... more Research on coreference resolution and summarization has modeled the way entities are realized as concrete phrases in discourse. In particular there exist models of the noun phrase syntax used for discourse-new versus discourse-old referents, and models describing the likely distance between a pronoun and its antecedent. However, models of discourse coherence, as applied to information ordering tasks, have ignored these kinds of information. We apply a discourse-new classifier and pronoun coreference algorithm to the information ordering task, and show significant improvements in performance over the entity grid, a popular model of local coherence.
ANLP/NAACL 2000 Workshop on Reading comprehension tests as evaluation for computer-based language understanding sytems -, 2000
International Joint Conference on Artificial Intelligence, 1977
this paper (see[Schank 86] for a theoretical discussion and [Kass 86] and [Leake and Owens 86] fo... more this paper (see[Schank 86] for a theoretical discussion and [Kass 86] and [Leake and Owens 86] forbrief discussions of a program built around these .principles); the goal here is simplyto point out how our interest in natural language processing has led us naturally,and indeed inevitably, to develop theories of explanation and creativity. Some maysay that we have strayed from the
Proceedings of the main conference on Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics -, 2006
We present a PCFG parsing algorithm that uses a multilevel coarse-to-fine (mlctf) scheme to impro... more We present a PCFG parsing algorithm that uses a multilevel coarse-to-fine (mlctf) scheme to improve the efficiency of search for the best parse. Our approach requires the user to specify a sequence of nested partitions or equivalence classes of the PCFG nonterminals. We define a sequence of PCFGs corresponding to each partition, where the nonterminals of each PCFG are clusters of nonterminals of the original source PCFG. We use the results of parsing at a coarser level (i.e., grammar defined in terms of a coarser partition) to prune the next finer level. We present experiments showing that with our algorithm the work load (as measured by the total number of constituents processed) is decreased by a factor of ten with no decrease in parsing accuracy compared to standard CKY parsing with the original PCFG. We suggest that the search space over mlctf algorithms is almost totally unexplored so that future work should be able to improve significantly on these results.
Language Resources and Evaluation, 2004
This paper describes a method for conducting evaluations of Treebank and non-Treebank parsers ali... more This paper describes a method for conducting evaluations of Treebank and non-Treebank parsers alike against the English language U. Penn Treebank (Marcus et al., 1993) using a metric that focuses on the accuracy of relatively non-controversial aspects of parse structure. Our conjecture is that if we focus on maximal projections of heads (MPH), we are likely to find much broader
Journal of the American Statistical Association, 1994
... But equally important, the idea of learning a language is a fascinating one in its own right,... more ... But equally important, the idea of learning a language is a fascinating one in its own right, and it is ... 1.2 Morphology and Knowledge of Words The analysis of written language is typically divided into four parts: mor ... Most linguistic theories also assume that words have features. ...
IEEE Transactions on Pattern Analysis and Machine Intelligence, 1993
Computational Linguistics, 2010
When multiple conversations occur simultaneously, a listener must decide which conversation each ... more When multiple conversations occur simultaneously, a listener must decide which conversation each utterance is part of in order to interpret and respond to it appropriately. We refer to this task as disentanglement. We present a corpus of Internet Relay Chat dialogue in which the various conversations have been manually disentangled, and evaluate annotator reliability. We propose a graph-based clustering model for disentanglement, using lexical, timing, and discourse-based features. The model's predicted disentanglements are highly correlated with manual annotations. We conclude by discussing two extensions to the model, specificity tuning and conversation start detection, both of which are promising but do not currently yield practical improvements.
Artificial Intelligence, 1993
Abstract We argue that the problem of plan recognition, inferring an agent's plan fr... more Abstract We argue that the problem of plan recognition, inferring an agent's plan from observations, is largely a problem of inference under conditions of uncertainty. We present an approach to the plan recognition problem that is based on Bayesian probability theory. ...
Artificial Intelligence, 1994
Cost-based abduction attempts to find the best explanation for a set of facts by finding a minima... more Cost-based abduction attempts to find the best explanation for a set of facts by finding a minimal cost proof for the facts. The costs are computed by summing the costs of the assumptions necessary for the proof plus the cost of the rules. We examine existing methods for constructing ...
Meeting of the Association for Computational Linguistics, 2010
We investigate coreference relationships between NPs with the same head noun. It is relatively co... more We investigate coreference relationships between NPs with the same head noun. It is relatively common in unsupervised work to assume that such pairs are coreferent- but this is not always true, es- pecially if realistic mention detection is used. We describe the distribution of non- coreferent same-head pairs in news text, and present an unsupervised generative model which learns not
North American Chapter of the Association for Computational Linguistics, 2009
We describe a generative model for clustering named entities which also models named en- tity int... more We describe a generative model for clustering named entities which also models named en- tity internal structure, clustering related words by role. The model is entirely unsupervised; it uses features from the named entity itself and its syntactic context, and coreference in- formation from an unsupervised pronoun re- solver. The model scores 86% on the MUC-7 named-entity dataset. To our
Meeting of the Association for Computational Linguistics, 2008
Research on coreference resolution and sum- marization has modeled the way entities are realized ... more Research on coreference resolution and sum- marization has modeled the way entities are realized as concrete phrases in discourse. In particular there exist models of the noun phrase syntax used for discourse-new versus discourse-old referents, and models describ- ing the likely distance between a pronoun and its antecedent. However, models of discourse coherence, as applied to information ordering tasks, have
Conference of the European Chapter of the Association for Computational Linguistics, 2009
We present an algorithm for pronoun- anaphora (in English) that uses Expecta- tion Maximization (... more We present an algorithm for pronoun- anaphora (in English) that uses Expecta- tion Maximization (EM) to learn virtually all of its parameters in an unsupervised fashion. While EM frequently fails to find good models for the tasks to which it is set, in this case it works quite well. We have compared it to several systems avail- able on the
Meeting of the Association for Computational Linguistics, 2008
When multiple conversations occur simultane- ously, a listener must decide which conversa- tion e... more When multiple conversations occur simultane- ously, a listener must decide which conversa- tion each utterance is part of in order to inter- pret and respond to it appropriately. We refer to this task as disentanglement. We present a corpus of Internet Relay Chat (IRC) dialogue in which the various conversations have been manually disentangled, and evaluate annota- tor reliability. This
National Conference on Artificial Intelligence, 1991
Plan-recognition requires the construction of possible plans which could explain a set of observe... more Plan-recognition requires the construction of possible plans which could explain a set of observed actions, and then selecting one or more of them as providing the best explanation. In this paper we present a formal model of the latter process based upon probability theory. Our model ...
Meeting of the Association for Computational Linguistics, 1999
We present a method for extracting parts of objects from wholes (e.g. "speedometer" fro... more We present a method for extracting parts of objects from wholes (e.g. "speedometer" from "car"). Given a very large corpus our method finds part words with 55% accuracy for the top 50 words as ranked by the system. The part list could be scanned by an end-user and added to an existing ontology (such as WordNet), or used as a
Proceedings of the 46th Annual Meeting of the Association for Computational Linguistics on Human Language Technologies Short Papers - HLT '08, 2008
Research on coreference resolution and summarization has modeled the way entities are realized as... more Research on coreference resolution and summarization has modeled the way entities are realized as concrete phrases in discourse. In particular there exist models of the noun phrase syntax used for discourse-new versus discourse-old referents, and models describing the likely distance between a pronoun and its antecedent. However, models of discourse coherence, as applied to information ordering tasks, have ignored these kinds of information. We apply a discourse-new classifier and pronoun coreference algorithm to the information ordering task, and show significant improvements in performance over the entity grid, a popular model of local coherence.
ANLP/NAACL 2000 Workshop on Reading comprehension tests as evaluation for computer-based language understanding sytems -, 2000
International Joint Conference on Artificial Intelligence, 1977
this paper (see[Schank 86] for a theoretical discussion and [Kass 86] and [Leake and Owens 86] fo... more this paper (see[Schank 86] for a theoretical discussion and [Kass 86] and [Leake and Owens 86] forbrief discussions of a program built around these .principles); the goal here is simplyto point out how our interest in natural language processing has led us naturally,and indeed inevitably, to develop theories of explanation and creativity. Some maysay that we have strayed from the
Proceedings of the main conference on Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics -, 2006
We present a PCFG parsing algorithm that uses a multilevel coarse-to-fine (mlctf) scheme to impro... more We present a PCFG parsing algorithm that uses a multilevel coarse-to-fine (mlctf) scheme to improve the efficiency of search for the best parse. Our approach requires the user to specify a sequence of nested partitions or equivalence classes of the PCFG nonterminals. We define a sequence of PCFGs corresponding to each partition, where the nonterminals of each PCFG are clusters of nonterminals of the original source PCFG. We use the results of parsing at a coarser level (i.e., grammar defined in terms of a coarser partition) to prune the next finer level. We present experiments showing that with our algorithm the work load (as measured by the total number of constituents processed) is decreased by a factor of ten with no decrease in parsing accuracy compared to standard CKY parsing with the original PCFG. We suggest that the search space over mlctf algorithms is almost totally unexplored so that future work should be able to improve significantly on these results.
Language Resources and Evaluation, 2004
This paper describes a method for conducting evaluations of Treebank and non-Treebank parsers ali... more This paper describes a method for conducting evaluations of Treebank and non-Treebank parsers alike against the English language U. Penn Treebank (Marcus et al., 1993) using a metric that focuses on the accuracy of relatively non-controversial aspects of parse structure. Our conjecture is that if we focus on maximal projections of heads (MPH), we are likely to find much broader
Journal of the American Statistical Association, 1994
... But equally important, the idea of learning a language is a fascinating one in its own right,... more ... But equally important, the idea of learning a language is a fascinating one in its own right, and it is ... 1.2 Morphology and Knowledge of Words The analysis of written language is typically divided into four parts: mor ... Most linguistic theories also assume that words have features. ...
IEEE Transactions on Pattern Analysis and Machine Intelligence, 1993
Computational Linguistics, 2010
When multiple conversations occur simultaneously, a listener must decide which conversation each ... more When multiple conversations occur simultaneously, a listener must decide which conversation each utterance is part of in order to interpret and respond to it appropriately. We refer to this task as disentanglement. We present a corpus of Internet Relay Chat dialogue in which the various conversations have been manually disentangled, and evaluate annotator reliability. We propose a graph-based clustering model for disentanglement, using lexical, timing, and discourse-based features. The model's predicted disentanglements are highly correlated with manual annotations. We conclude by discussing two extensions to the model, specificity tuning and conversation start detection, both of which are promising but do not currently yield practical improvements.
Artificial Intelligence, 1993
Abstract We argue that the problem of plan recognition, inferring an agent's plan fr... more Abstract We argue that the problem of plan recognition, inferring an agent's plan from observations, is largely a problem of inference under conditions of uncertainty. We present an approach to the plan recognition problem that is based on Bayesian probability theory. ...
Artificial Intelligence, 1994
Cost-based abduction attempts to find the best explanation for a set of facts by finding a minima... more Cost-based abduction attempts to find the best explanation for a set of facts by finding a minimal cost proof for the facts. The costs are computed by summing the costs of the assumptions necessary for the proof plus the cost of the rules. We examine existing methods for constructing ...