Christopher D. Manning

Enforcing Transitivity in Coreference Resolution (2009)

Jenny Rose Finkel, Christopher D. Manning

A desirable quality of a coreference resolution system is the ability to handle transitivity constraints, such that even if it places high likelihood on a particular mention being coreferent with...

An (2009)

Bill Maccartney, Christopher D. Manning

extended model of natural logic

Optimizing Chinese Word Segmentation for Machine Translation Performance (2009)

Pi-chuan Chang, Michel Galley, Christopher D. Manning

Previous work has shown that Chinese word segmentation is useful for machine translation to English, yet the way different segmentation strategies affect MT is still poorly understood. In this paper,...

Regularization and Search for Minimum Error Rate Training (2009)

Daniel Cer, Daniel Jurafsky, Christopher D. Manning

Minimum error rate training (MERT) is a widely used learning procedure for statistical machine translation models. We contrast three search strategies for MERT: Powell’s method, the variant of...

This document describes Stanford University’s first (2009)

Michel Galley, Pi-chuan Chang, Daniel Cer, Jenny R. Finkel, Christopher D. Manning, Michel Galley

entry into a NIST MT evaluation. Our entry to the 2008 evaluation mainly focused on establishing a competent baseline with a phrase-based system similar to (Och and Ney, 2004; Koehn et al., 2007). In...

A Phrase-Based Alignment Model for Natural Language Inference (2009)

Bill Maccartney, Michel Galley, Christopher D. Manning

The alignment problem—establishing links between corresponding phrases in two related sentences—is as important in natural language inference (NLI) as it is in machine translation (MT). But the...

Symbolic Systems (2009)

David Hall, Daniel Jurafsky, Christopher D. Manning

How can the development of ideas in a scientific field be studied over time? We apply unsupervised topic modeling to the ACL Anthology to analyze historical trends in the field of Computational...

Learning Alignments and Leveraging Natural Logic (2008)

Nathanael Chambers, Daniel Cer, Trond Grenager, David Hall, Chloe Kiddon, Bill Maccartney, ...

We describe an approach to textual inference that improves alignments at both the typed dependency level and at a deeper semantic level. We present a machine learning approach to alignment scoring, a...

Learning Alignments and Leveraging Natural Logic (2008)

Nathanael Chambers, Daniel Cer, Trond Grenager, David Hall, Chloe Kiddon, Bill Maccartney, ...

We describe an approach to textual inference that improves alignments at both the typed dependency level and at a deeper semantic level. We present a machine learning approach to alignment scoring, a...

Special issue on “Probabilistic models of cognition (2008)

Nick Chater, Christopher D. Manning

Probabilistic methods are providing new explanatory approaches to fundamental cognitive science questions of how humans structure, process and acquire language. This review examines probabilistic...

Abstract (2008)

Dan Klein, Christopher D. Manning

We present a novel generative model for natural language tree structures in which semantic (lexical dependency) and syntactic (PCFG) structures are scored with separate models. This factorization...

Review TRENDS in Cognitive Sciences Vol.10 No.7 July 2006 Special Issue: Probabilistic models of cognition Probabilistic models of language processing and acquisition (2008)

Nick Chater, Christopher D. Manning

Probabilistic methods are providing new explanatory approaches to fundamental cognitive science questions of how humans structure, process and acquire language. This review examines probabilistic...

Abstract (2008)

Ofer Dekel, Christopher D. Manning, Yoram Singer

Label ranking is the task of inferring a total order over a predefined set of labels for each given instance. We present a general framework for batch learning of label ranking functions from...

Review TRENDS in Cognitive Sciences Vol.10 No.7 July 2006 Special Issue: Probabilistic models of cognition Probabilistic models of language processing and acquisition (2008)

Nick Chater, Christopher D. Manning

Probabilistic methods are providing new explanatory approaches to fundamental cognitive science questions of how humans structure, process and acquire language. This review examines probabilistic...

Abstract (2008)

Dan Klein, Christopher D. Manning

We present a generative model for the unsupervised learning of dependency structures. We also describe the multiplicative combination of this dependency model with a model of linear constituency. The...

K.L.Melmon, “What's related? Generalizing approaches to related articles (2008)

Howard R. Strasberg, Christopher D. Manning, Ph. D, Thomas C. Rindfleisch, Kenneth L. Melmon

INTRODUCTION: We did formative evaluations of several variations to the computation of related articles for non-bibliographic resources in the medical domain. METHODS: A binary mo del and several...

Abstract (2008)

Dan Klein, Christopher D. Manning

We present a novel generative model for natural language tree structures in which semantic (lexical dependency) and syntactic (PCFG) structures are scored with separate models. This factorization...

Using Feature Conjunctions across Examples for Learning Pairwise Classifiers (2008)

Satoshi Oyama, Christopher D. Manning

Abstract. We propose a kernel method for using combinations of features across example pairs in learning pairwise classifiers. Identifying two instances in the same class is an important technique in...

Lexical And Constructional Aspects of Linguistic Explanation. (2008)

Christopher D. Manning, Ivan A. Sag, In Pollard, The Subcategorized, Gert Webelhuth, Jean-pierre Koenig, ...

arguments of a head are stored on a single ordered list, the subcat list. However, Borsley (1989) argues that there are various deficiencies in this approach, and suggests that the unified list...

Optimizing Local Probability Models for Statistical Parsing (2008)

Kristina Toutanova, Mark Mitchell, Christopher D. Manning

Abstract. This paper studies the properties and performance of models for estimating local probability distributions which are used as components of larger probabilistic systems — history-based...

Lexical And Constructional Aspects of Linguistic Explanation. (2008)

Christopher D. Manning, Ivan A. Sag, In Pollard, The Subcategorized, Gert Webelhuth, Jean-pierre Koenig, ...

arguments of a head are stored on a single ordered list, the subcat list. However, Borsley (1989) argues that there are various deficiencies in this approach, and suggests that the unified list...

Abstract (2008)

Ofer Dekel, Christopher D. Manning, Yoram Singer

Label ranking is the task of inferring a total order over a predefined set of labels for each given instance. We present a general framework for batch learning of label ranking functions from...

Optimizing Local Probability Models for StatisticalParsing (2008)

Kristina Toutanova, Mark Mitchell, Christopher D. Manning

Abstract. This paper studies the properties and performance of models for es-timating local probability distributions which are used as components of larger probabilistic systems-- history-based...

Abstract (2008)

Dan Klein, Christopher D. Manning

We present a novel generative model for natural language tree structures in which semantic (lexical dependency) and syntactic (PCFG) structures are scored with separate models. This factorization...

Reviewed by (2008)

Christopher D. Manning, Hinrich Schütze, Ma The, Mit Press, Lillian Lee

time, empirical techniques to natural language processing were on the rise — in that year, Computational Linguistics published a special issue on such methods — and Charniak’s text was the...

Abstract (2008)

Ofer Dekel, Christopher D. Manning, Yoram Singer

Label ranking is the task of inferring a total order over a predefined set of labels for each given instance. We present a general framework for batch learning of label ranking functions from...

To appear in in Literary and Linguistic Computing, 16(1): 123–139, 2001. Kirrkirr: Software for browsing and visual exploration of a structured Warlpiri dictionary (2008)

Christopher D. Manning, Kevin Jansz, Nitin Indurkhya, Christopher Manning

This paper presents an overview of the goals, architecture, and usability of Kirrkirr, a Java-based visualization tool for XML dictionaries, currently being used with a dictionary for Warlpiri, an...

To appear in Literary andLinguistic Computing 16(1): , 123–139, 2001. Kirrkirr: Softwarefor browsingandvisual explorat ionof a structuredWarlpiri dictionary (2008)

Christopher D. Manning, Kevin Jansz

This paper presents an overviewof the goals, archi tecture, and usability of Kirrkirr, Java-based a visualization tool for XMLdictionaries, currently being usedwith dictionary a forWarlpiri, an...

Finding contradictions in text (2008)

Anna N. Rafferty, Christopher D. Manning

Detecting conflicting statements is a foundational text understanding task with applications in information analysis. We propose an appropriate definition of contradiction for NLP tasks and develop...

Efficient, feature-based, conditional random field parsing (2008)

Jenny Rose Finkel, Alex Kleeman, Christopher D. Manning

Discriminative feature-based methods are widely used in natural language processing, but sentence parsing is still dominated by generative methods. While prior feature-based dynamic programming...

Voice and grammatical relations in Indonesian: A new perspective (2007)

Wayan Arka Christopher, Christopher D. Manning

This paper deals with the voice system of Indonesian, and argues that certain of the constructions traditionally analysed as passives, should be given a different treatment, parallel to arguments by...

What's Related? Generalizing Approaches to Related Articles in Medicine (2007)

Howard Strasberg Christopher, Christopher D. Manning, Ph. D, Thomas C. Rindfleisch, Kenneth L. Melmon

INTRODUCTION: We did formative evaluations of several variations to the computation of related articles for nonbibliographic resources in the medical domain. METHODS: A binary model and several...

Voice and grammatical relations in Indonesian: A new perspective (2007)

Wayan Arka, Christopher D. Manning

This paper deals with the voice system of Indonesian, and argues that certain of the constructions traditionally analysed as passives, should be given a different treatment, parallel to arguments by...

Voice and grammatical relations in Indonesian: A new perspective (2007)

Wayan Arka, Christopher D. Manning

This paper deals with the voice system of Indonesian, and argues that certain of the constructions traditionally analysed as passives, should be given a different treatment, parallel to arguments by...

Pages 1--8 Inducing Novel Gene-Drug Interactions from the Biomedical Literature (2007)

Sepandar D. Kamvar, Diane E. Oliver, Christopher D. Manning, Russ B. Altman

Motivation: Knowledge about the interactions between genes and drugs is important in determining the efficacy and toxicity of medications. We present a supervised learning algorithm for inducing...

I l (2007)

Christopher D. Manning

The segmentation problem in morphology learning Recently there has been a large literature on various approaches to learning morphology, and the success and cognitive plausibility of different...

1 The Tradition of Categoricity and Prospects for Stochasticity (2007)

Christopher D. Manning

"Everyone knows that language is variable. " This is the bald sentence with which Sapir (1921:147) begins his chapter on language as an historical product. He goes on to emphasize...

Reviewed by (2007)

Christopher D. Manning, Hinrich Schiitze, Lillian Lee

At the time, empirical techniques for natural language processing were on the rise; that year, Computational Linguistics published a special issue on such methods, and Charniak's text was the...

What’s needed for lexical databases? Experiences with Kirrkirr (2007)

Christopher D. Manning

This paper discusses what is required from dictionary databases, and one approach, based on experience with Kirrkirr, a dictionary browser originally developed for Warlpiri, an Indigenous Australian...

Abstract While O(n (2007)

Dan Klein, Christopher D. Manning

) methods for parsing probabilistic context-free grammars (PCFGs) are well known, a tabular parsing framework for arbitrary PCFGs which allows for botton-up, topdown, and other parsing strategies,...

1 The Tradition of Categoricity and Prospects for Stochasticity (2007)

Christopher D. Manning

Everyone knows that language is variable. This is the bald sentence with which Sapir (1921:147) begins his chapter on language as a historical product. He goes on to emphasize how two speakers'...

LinGO Redwoods (2007)

Rich And Dynamic, Lingo Redwoods, Stephan Oepen, Ezra Callahan, Dan Flickinger, Christopher D. Manning, ...

The LinGO Redwoods initiative is a seed activity in the design and development of a new type of treebank. A treebank is a (typically hand-built) collection of natural language utterances and...

Combining Heterogeneous Classi (2007)

H. Tolga Ilhan, Ar D. Kamvar, Dan Klein, Christopher D. Manning, Kristina Toutanova

The Stanford-CS224N system is an ensemble of simple classi ers. The rst-tier systems are heterogeneous, consisting primarily of naive-Bayes variants, but also including vector space, memory-based,...

2 and Huy Nguyen (2007)

Dan Klein, Joseph Smarr, Christopher D. Manning

We discuss two named-entity recognition models which use characters and character n-grams either exclusively or as an important part of their data representation. The first model is a character-level...

Aligning semantic graphs for textual inference and machine reading (2007)

Trond Grenager, Bill Maccartney, Daniel Cer, Daniel Ramage, Chloé Kiddon, ...

This paper presents our work on textual inference and situates it within the context of the larger goals of machine reading. The textual inference task is to determine if the meaning of one text can...

The infinite tree (2007)

Jenny Rose Finkel, Trond Grenager, Christopher D. Manning

Historically, unsupervised learning techniques have lacked a principled technique for selecting the number of unseen components. Research into non-parametric priors, such as the Dirichlet process,...

The infinite tree (2007)

Jenny Rose Finkel, Trond Grenager, Christopher D. Manning

Historically, unsupervised learning techniques have lacked a principled technique for selecting the number of unseen components. Research into non-parametric priors, such as the Dirichlet process,...

Aligning semantic graphs for textual inference and machine reading (2007)

Trond Grenager, Bill Maccartney, Daniel Cer, Daniel Ramage, Chloé Kiddon, ...

This paper presents our work on textual inference and situates it within the context of the larger goals of machine reading. The textual inference task is to determine if the meaning of one text can...

The infinite tree (2007)

Jenny Rose Finkel, Trond Grenager, Christopher D. Manning

Historically, unsupervised learning techniques have lacked a principled technique for selecting the number of unseen components. Research into non-parametric priors, such as the Dirichlet process,...

Natural logic for textual inference (2007)

Bill Maccartney, Christopher D. Manning

This paper presents the first use of a computational model of natural logic—a system of logical inference which operates over natural language—for textual inference. Most current approaches to...

Learning Alignments and Leveraging Natural Logic (2007)

Nathanael Chambers, Daniel Cer, Trond Grenager, David Hall, Chloe Kiddon, Bill Maccartney, ...

We describe an approach to textual inference that improves alignments at both the typed dependency level and at a deeper semantic level. We present a machine learning approach to alignment scoring, a...

Learning to Recognize Features of Valid Textual Entailments (2006)

MacCartney, Bill, Grenager, Trond, Marneffe, Marie-Catherine De, Cer, Daniel, Manning, Christopher D.

This paper advocates a new architecture for textual inference in which finding a good alignment is separated from evaluating entailment. Current approaches to semantic inference in question answering...

Learning to recognize features of valid textual entailments (2006)

Bill Maccartney, Trond Grenager, Daniel Cer, Christopher D. Manning

This paper advocates a new architecture for textual inference in which finding a good alignment is separated from evaluating entailment. Current approaches to semantic inference in question answering...

Learning to recognize features of valid textual entailments (2006)

Bill Maccartney, Trond Grenager, Daniel Cer, Christopher D. Manning

This paper advocates a new architecture for textual inference in which finding a good alignment is separated from evaluating entailment. Current approaches to semantic inference in question answering...

Solving the problem of cascading errors: Approximate bayesian inference for linguistic annotation pipelines (2006)

Jenny Rose Finkel, Christopher D. Manning, Andrew Y. Ng

The end-to-end performance of natural language processing systems for compound tasks, such as question answering and textual entailment, is often hampered by use of a greedy 1-best pipeline...

An effective two-stage model for exploiting non-local dependencies in named entity recognition (2006)

Vijay Krishnan, Christopher D. Manning

This paper shows that a simple two-stage approach to handle non-local dependencies in Named Entity Recognition (NER) can outperform existing approaches that handle non-local dependencies, while being...

Learning to distinguish valid textual entailments (2006)

Bill Maccartney, Trond Grenager, Daniel Cer, Anna Rafferty, Christopher D. Manning

This paper proposes a new architecture for textual inference in which finding a good alignment is separated from evaluating entailment. Current approaches to semantic inference in question answering...

Generating typed dependency parses from phrase structure parses (2006)

Bill Maccartney, Christopher D. Manning

This paper describes a system for extracting typed dependency parses of English sentences from phrase structure parses. In order to capture inherent relations occurring in corpus texts that can be...

LOCAL TEXTUAL INFERENCE: IT’S HARD TO CIRCUMSCRIBE, BUT YOU KNOW IT WHEN YOU SEE IT – AND NLP NEEDS IT (2006)

Christopher D. Manning

Technology for local textual inference is central to producing a next generation of intelligent yet robust human language processing systems. One can think of it as Information Retrieval++. It is...

Learning to distinguish valid textual entailments (2006)

Bill Maccartney, Trond Grenager, Daniel Cer, Anna Rafferty, Christopher D. Manning

This paper proposes a new architecture for textual inference in which finding a good alignment is separated from evaluating entailment. Current approaches to semantic inference in question answering...

Solving the problem of cascading errors: Approximate bayesian inference for linguistic annotation pipelines (2006)

Jenny Rose Finkel, Christopher D. Manning, Andrew Y. Ng

The end-to-end performance of natural language processing systems for compound tasks, such as question answering and textual entailment, is often hampered by use of a greedy 1-best pipeline...

Learning to recognize features of valid textual entailments (2006)

Bill Maccartney, Trond Grenager, Daniel Cer, Christopher D. Manning

This paper advocates a new architecture for textual inference in which finding a good alignment is separated from evaluating entailment. Current approaches to semantic inference in question answering...

Generating typed dependency parses from phrase structure parses (2006)

Bill Maccartney, Christopher D. Manning

This paper describes a system for extracting typed dependency parses of English sentences from phrase structure parses. In order to capture inherent relations occurring in corpus texts that can be...

An effective two-stage model for exploiting non-local dependencies in named entity recognition (2006)

Vijay Krishnan, Christopher D. Manning

This paper shows that a simple two-stage approach to handle non-local dependencies in Named Entity Recognition (NER) can outperform existing approaches that handle non-local dependencies, while being...

Exploring the boundaries: gene and protein identification in biomedical text (2005)

Finkel, Jenny, Dingare, Shipra, Manning, Christopher D, Nissim, Malvina, Alex, Beatrice, Grover, Claire

Abstract Background Good automatic information extraction tools offer hope for automatic processing of the exploding biomedical literature, and successful named entity recognition is a key component...

Robust textual inference via learning and abductive reasoning (2005)

Rajat Raina, Andrew Y. Ng, Christopher D. Manning

We present a system for textual inference (the task of inferring whether a sentence follows from another text) that uses learning and a logical-formula semantic representation of the text. More...

Robust textual inference using diverse knowledge sources (2005)

Rajat Raina, Aria Haghighi, Christopher Cox, Jenny Finkel, Jeff Michels, Kristina Toutanova, ...

We present a machine learning approach to robust textual inference, in which parses of the text and the hypothesis sentences are used to measure their asymmetric “similarity”, and thereby to...

Exploring the boundaries: gene and protein identification in biomedical text (2005)

Bmc Bioinformatics, Jenny Finkel, Shipra Dingare, Christopher D Manning, Malvina Nissim, Beatrice Alex, ...

Background: Good automatic information extraction tools offer hope for automatic processing of the exploding biomedical literature, and successful named entity recognition is a key component for such...

Robust textual inference via learning and abductive reasoning (2005)

Rajat Raina, Andrew Y. Ng, Christopher D. Manning

We present a system for textual inference (the task of inferring whether a sentence follows from another text) that uses learning and a logical-formula semantic representation of the text. More...

REFERENCES (2005)

Kristina N. Toutanova, Christopher D. Manning, Andrew Y. Ng, Robert C. Moore

Research Intern Implemented a statistical model for automatic spelling correction, which combines letterbased and phone-based knowledge.

Joint learning improves semantic role labeling. InProceedingsofACL-2005 (2005)

Kristina Toutanova, Aria Haghighi, Christopher D. Manning

Despite much recent progress on accurate semantic role labeling, previous work has largely used independent classifiers, possibly combined with separate label sequence models via Viterbi decoding....

Exploring the boundaries: Gene and protein identification in biomedical text (2004)

Jenny Finkel, Shipra Dingare, Christopher D. Manning, Malvina Nissim, Beatrice Alex, Claire Grover

Background: Good automatic information extraction tools offer hope for automatic processing of the exploding biomedical literature, and successful named entity recognition is a key component for such...

Learning random walk models for inducing word dependency distributions (2004)

Kristina Toutanova, Christopher D. Manning, Andrew Y. Ng

Many NLP tasks rely on accurately estimating word dependency probabilities P(w 1

Learning random walk models for inducing word dependency distributions (2004)

Kristina Toutanova, Christopher D. Manning, Andrew Y. Ng

Many NLP tasks rely on accurately estimating word dependency probabilities P(w 1

Using Feature Conjunctions across Examples for Learning Pairwise Classifiers (2004)

Satoshi Oyama, Christopher D. Manning

We propose a kernel method for using combinations of features across example pairs in learning pairwise classifiers. Identifying two instances in the same class is an important technique in duplicate...

Learning random walk models for inducing word dependency distributions (2004)

Kristina Toutanova, Christopher D. Manning, Andrew Y. Ng

Many NLP tasks rely on accurately estimating word dependency probabilities P(w1|w2), where the words w1 and w2 have a particular relationship (such as verb-object). Because of the sparseness of...

Solving logic puzzles: From robust processing to precise semantics (2004)

Iddo Lev, Bill Maccartney, Christopher D. Manning, Roger Levy

This paper presents intial work on a system that bridges from robust, broad-coverage natural language processing to precise semantics and automated reasoning, focusing on solving logic puzzles drawn...

Learning random walk models for inducing word dependency distributions (2004)

Kristina Toutanova, Christopher D. Manning, Andrew Y. Ng

Many NLP tasks rely on accurately estimating word dependency probabilities P(w1|w2), where the words w1 and w2 have a particular relationship (such as verb-object). Because of the sparseness of...

Solving logic puzzles: From robust processing to precise semantics (2004)

Iddo Lev, Bill Maccartney, Christopher D. Manning, Roger Levy

This paper presents intial work on a system that bridges from robust, broad-coverage natural language processing to precise semantics and automated reasoning, focusing on solving logic puzzles drawn...

Learning random walk models for inducing word dependency distributions (2004)

Kristina Toutanova, Christopher D. Manning, Andrew Y. Ng

Many NLP tasks rely on accurately estimating word dependency probabilities P(w1|w2), where the words w1 and w2 have a particular relationship (such as verb-object). Because of the sparseness of...

Learning random walk models for inducing word dependency distributions (2004)

Kristina Toutanova, Christopher D. Manning, Andrew Y. Ng

Many NLP tasks rely on accurately estimating word dependency probabilities P(w1|w2), where the words w1 and w2 have a particular relationship (such as verb-object). Because of the sparseness of...

Exploring the boundaries: Gene and protein identification in biomedical text (2004)

Jenny Finkel, Shipra Dingare, Christopher D. Manning, Malvina Nissim, Beatrice Alex, Claire Grover

Background: Good automatic information extraction tools offer hope for automatic processing of the exploding biomedical literature, and successful named entity recognition is a key component for such...

Extrapolation Methods for Accelerating PageRank Computations (2003)

Kamvar, Sepandar D., Haveliwala, Taher H., Manning, Christopher D., Golub, Gene H.

We present a novel algorithm for the fast computation of PageRank, a hyperlink-based estimate of the ''importance'' of Web pages. The original PageRank algorithm uses the Power Method to compute...

Feature-Rich Part-of-Speech Tagging with a Cyclic Dependency Network (2003)

Kristina Toutanova, Dan Klein, Christopher D. Manning, Yoram Singer

We present a new part-of-speech tagger that demonstrates the following ideas: (i) explicit use of both preceding and following tag contexts via a dependency network representation, (ii) broad use of...

Accurate Unlexicalized Parsing (2003)

Dan Klein, Christopher D. Manning

We demonstrate that an unlexicalized PCFG can parse much more accurately than previously shown, by making use of simple, linguistically motivated state splits, which break down false independence...

Spectral learning (2003)

Sepandar D. Kamvar, Dan Klein, Christopher D. Manning

We present a simple, easily implemented spectral learning algorithm which applies equally whether we have no supervisory information, pairwise link constraints, or labeled examples. In the...

Extrapolation methods for accelerating pagerank computations (2003)

Sepandar D. Kamvar, Taher H. Haveliwala, Christopher D. Manning, Gene H. Golub

We present a novel algorithm for the fast computation of PageRank, a hyperlink-based estimate of the "importance " of Web pages. The original PageRank algorithm uses the Power...

Extrapolation methods for accelerating pagerank computations (2003)

Sepandar D. Kamvar, Taher H. Haveliwala, Christopher D. Manning, Gene H. Golub

We present a novel algorithm for the fast computation of PageRank, a hyperlink-based estimate of the "importance " of Web pages. The original PageRank algorithm uses the Power...

Named entity recognition with character-level models (2003)

Dan Klein, Joseph Smarr, Huy Nguyen, Christopher D. Manning

We discuss two named-entity recognition models which use characters and character n-grams either exclusively or as an important part of their data representation. The first model is a character-level...

Feature-Rich Part-of-Speech Tagging with a Cyclic Dependency Network (2003)

Kristina Toutanova, Dan Klein, Christopher D. Manning, Yoram Singer

We present a new part-of-speech tagger that demonstrates the following ideas: (i) explicit use of both preceding and following tag contexts via a dependency network representation, (ii) broad use of...

Exploiting the Block Structure of the Web for Computing (2003)

Sepandar D. Kamvar, Taher H. Haveliwala, Christopher D. Manning, Gene H. Golub

The web link graph has a nested block structure: the vast majority of hyperlinks link pages on a host to other pages on the same host, and many of those that do not link pages within the same domain....

Exploiting the Block Structure of the Web for Computing (2003)

Sepandar D. Kamvar, Taher H. Haveliwala, Christopher D. Manning, Gene H. Golub

The web link graph has a nested block structure: the vast majority of hyperlinks link pages on a host to other pages on the same host, and many of those that do not link pages within the same domain....

Spectral learning (2003)

Sepandar D. Kamvar, Dan Klein, Christopher D. Manning

We present a simple, easily implemented spectral learning algorithm that applies equally whether we have no supervisory information, pairwise link constraints, or labeled examples. In the...

Exploiting the Block Structure of the Web for Computing (2003)

Sepandar D. Kamvar, Taher H. Haveliwala, Christopher D. Manning, Gene H. Golub

The web link graph has a nested block structure: the vast majority of hyperlinks link pages on a host to other pages on the same host, and many of those that do not link pages within the same domain....

Extrapolation methods for accelerating pagerank computations (2003)

Sepandar D. Kamvar, Taher H. Haveliwala, Christopher D. Manning, Gene H. Golub

We present a novel algorithm for the fast computation of PageRank, a hyperlink-based estimate of the "importance " of Web pages. The original PageRank algorithm uses the Power...

Accurate Unlexicalized Parsing (2003)

Dan Klein, Christopher D. Manning

We demonstrate that an unlexicalized PCFG can parse much more accurately than previously shown, by making use of simple, linguistically motivated state splits, which break down false independence...

Exploiting the Block Structure of the Web for Computing PageRank (2003)

Sepandar D. Kamvar, Taher H. Haveliwala, Christopher D. Manning, Gene H. Golub

The web link graph has a nested block structure: the vast majority of hyperlinks link pages on a host to other pages on the same host, and many of those that do not link pages within the same domain....

Accurate Unlexicalized Parsing (2003)

Dan Klein Stanford, Dan Klein, Christopher D. Manning

We demonstrate that an unlexicalized PCFG can parse much more accurately than previously shown, by making use of simple, linguistically motivated state splits, which break down false independence...

A* Parsing: Fast Exact Viterbi Parse Selection (2003)

Dan Klein, Christopher D. Manning

We present an extension of the classic A* search procedure to tabular PCFG parsing. The use of A* search can dramatically reduce the time required to find a best parse by conservatively estimating...

Named Entity Recognition with Character-Level Models (2003)

Dan Klein And, Dan Klein, Joseph Smarr, Huy Nguyen, Christopher D. Manning

We discuss two named-entity recognition models which use characters and character -grams either exclusively or as an important part of their data representation. The first model is a character-level...

Fast Exact Inference with a Factored Model for Natural Language Parsing (2003)

Dan Klein, Christopher D. Manning

We present a novel generative model for natural language tree structures in which semantic (lexical dependency) and syntactic (PCFG) structures are scored with separate models. This factorization...

A generative model for semantic role labeling (2003)

Cynthia A. Thompson, Roger Levy, Christopher D. Manning

Abstract. Determining the semantic role of sentence constituents is a key task in determining sentence meanings lying behind a veneer of variant syntactic expression. We present a model of natural...

Accurate Unlexicalized Parsing (2003)

Dan Klein Stanford, Dan Klein, Christopher D. Manning

We demonstrate that an unlexicalized PCFG can parse much more accurately than previously shown, by making use of simple, linguistically motivated state splits, which break down false independence...

Named Entity Recognition with Character-Level Models (2003)

Dan Klein Joseph, Joseph Smarr, Huy Nguyen, Christopher D. Manning

We discuss two named-entity recognition models which use characters and character n-grams either exclusively or as an important part of their data representation. The first model is a character-level...

Exploiting the Block Structure of the Web for Computing (2003)

Sepandar D. Kamvar, Taher H. Haveliwala, Christopher D. Manning, Gene H. Golub

The web link graph has a nested block structure: the vast majority of hyperlinks link pages on a host to other pages on the same host, and many of those that do not link pages within the same domain....

Accurate Unlexicalized Parsing (2003)

Dan Klein, Christopher D. Manning

We demonstrate that an unlexicalized PCFG can parse much more accurately than previously shown, by making use of simple, linguistically motivated state splits, which break down false independence...

Accurate Unlexicalized Parsing (2003)

Dan Klein, Christopher D. Manning

We demonstrate that an unlexicalized PCFG can parse much more accurately than previously shown, by making use of simple, linguistically motivated state splits, which break down false independence...

Feature-Rich Part-of-Speech Tagging with a Cyclic Dependency Network (2003)

Kristina Toutanova, Dan Klein, Christopher D. Manning, Yoram Singer

We present a new part-of-speech tagger that demonstrates the following ideas: (i) explicit use of both preceding and following tag contexts via a dependency network representation, (ii) broad use of...

Factored A* Search for Models over Sequences and Trees (2003)

Dan Klein, Christopher D. Manning

We investigate the calculation of A* bounds for sequence and tree models which are the explicit intersection of a set of simpler models or can be bounded by such an intersection. We provide a natural...

Abstract Parse Selection on the Redwoods Corpus: 3rd Growth Results (2003)

Kristina Toutanova, Christopher D. Manning, Stephan Oepen, Dan Flickinger

This report details experimental results of using stochastic disambiguation models for parsing sentences from the Redwoods treebank (Oepen et al., 2002). The goals of this paper are two-fold: (i) to...

Named entity recognition with character-level models (2003)

Dan Klein, Joseph Smarr, Huy Nguyen, Christopher D. Manning

We discuss two named-entity recognition models which use characters and character n-grams either exclusively or as an important part of their data representation. The first model is a character-level...

Abstract Parse Selection on the Redwoods Corpus: 3rd Growth Results (2003)

Kristina Toutanova, Christopher D. Manning, Stephan Oepen, Dan Flickinger

This report details experimental results of using stochastic disambiguation models for parsing sentences from the Redwoods treebank (Oepen et al., 2002). The goals of this paper are two-fold: (i) to...

Log-Linear Models for Label Ranking (2003)

Ofer Dekel, Christopher D. Manning, Yoram Singer

Label ranking is the task of inferring a total order over a predefined set of labels for each given instance. We present a general framework for batch learning of label ranking functions from...

Combining heterogeneous classifiers for word-sense disambiguation (2002)

Dan Klein, Kristina Toutanova, H. Tolga Ilhan, Ar D. Kamvar, Christopher D. Manning

This paper discusses ensembles of simple but heterogeneous classifiers for word-sense disambiguation, examining the Stanford-CS224N system entered in the SENSEVAL-2 English lexical sample task....

Interpreting and extending classical agglomerative clustering algorithms using a model-based approach (2002)

Sepandar D. Kamvar, Dan Klein, Christopher D. Manning

We present two results which arise from a model-based approach to hierarchical agglomerative clustering. First, we show formally that the common heuristic agglomerative clustering algorithms--...

From instance-level constraints to space-level constraints: Making the most of prior knowledge in data clustering (2002)

Dan Klein, Sepandar D. Kamvar, Christopher D. Manning

We present an improved method for clustering in the presence of very limited supervisory information, given as pairwise instance constraints. By allowing instance-level constraints to have spacelevel...

From instance-level constraints to space-level constraints: Making the most of prior knowledge in data clustering (2002)

Dan Klein, Sepandar D. Kamvar, Christopher D. Manning

We present an improved method for clustering in the presence of very limited supervisory information, given as pairwise instance constraints. By allowing instance-level constraints to have spacelevel...

From instance-level constraints to space-level constraints: Making the most of prior knowledge in data clustering (2002)

Dan Klein, Sepandar D. Kamvar, Christopher D. Manning

We present an improved method for clustering in the presence of very limited supervisory information, given as pairwise instance constraints. By allowing instance-level constraints to have spacelevel...

Conditional structure versus conditional estimation in NLP models (2002)

Dan Klein, Christopher D. Manning

This paper separates conditional parameter estimation, which consistently raises test set accuracy on statistical NLP tasks, from conditional model structures, such as the conditional Markov model...

Parse disambiguation for a rich hpsg grammar (2002)

Kristina Toutanova, Christopher D. Manning, Stuart M. Shieber, Þ Dan Flickinger, Stephan Oepen Ý

In this paper, we describe experiments on HPSG parse disambiguation using the Redwoods HPSG treebank (Oepen et al. 2002a,b,c). HPSG is a constraint-based lexicalist (“unification”) grammar...

Parse disambiguation for a rich hpsg grammar (2002)

Kristina Toutanova, Christopher D. Manning, Stuart M. Shieber, Dan Flickinger, Stephan Oepen

In this paper, we describe experiments on HPSG parse disambiguation using the Redwoods HPSG treebank (Oepen et al. 2002a,b,c). HPSG is a constraint-based lexicalist (“unification”) grammar...

Feature selection for a rich HPSG grammar using decision trees (2002)

Kristina Toutanova, Christopher D. Manning

This paper examines feature selection for log linear models over rich constraint-based grammar (HPSG) representations by building decision trees over features in corresponding probabilistic context...

Extentions to HMM-based statistical word alignment models (2002)

Kristina Toutanova, H. Tolga Ilhan, Christopher D. Manning

This paper describes improved HMM-based word level alignment models for statistical machine translation. We present a method for using part of speech tag information to improve alignment accuracy,...

Feature selection for a rich HPSG grammar using decision trees (2002)

Kristina Toutanova, Christopher D. Manning

This paper examines feature selection for log linear models over rich constraint-based grammar (HPSG) representations by building decision trees over features in corresponding probabilistic context...

Feature selection for a rich HPSG grammar using decision trees (2002)

Kristina Toutanova, Christopher D. Manning

This paper examines feature selection for log linear models over rich constraint-based grammar (HPSG) representations by building decision trees over features in corresponding probabilistic context...

Natural language grammar induction using a constituent-context model (2002)

Dan Klein, Christopher D. Manning

This paper presents a novel approach to the unsupervised learning of syntactic analyses of natural language text. Most previous work has focused on maximizing likelihood according to generative PCFG...

Combining heterogeneous classifiers for word-sense disambiguation (2002)

Dan Klein, Kristina Toutanova, H. Tolga Ilhan, Ar D. Kamvar, Christopher D. Manning

This paper discusses ensembles of simple but heterogeneous classifiers for word-sense disambiguation, examining the Stanford-CS224N system entered in the SENSEVAL-2 English lexical sample task....

Extensions to HMM-based Statistical Word Alignment Models (2002)

Kristina Toutanova Tolga, H. Tolga Ilhan, Christopher D. Manning

This paper describes improved HMM-based word level alignment models for statistical machine translation. We present a method for using part of speech tag information to improve alignment accuracy,...

Interpreting and Extending Classical Agglomerative Clustering Algorithms (2002)

Sepandar D. Kamvar, Dan Klein, Christopher D. Manning

We present two results which arise from a model-based approach to hierarchical agglomerative clustering. First, we show formally that the common heuristic agglomerative clustering algorithms --...

Parse Disambiguation for a Rich HPSG Grammar (2002)

Kristina Toutanova Christopher, Christopher D. Manning, Stuart M. Shieber, Dan Flickinger, Stephan Oepen

this paper, we describe experiments on HPSG parse disambiguation using the Redwoods HPSG treebank (Oepen et al. 2002a,b,c). HPSG is a constraint-based lexicalist ("unification") grammar...

Natural language grammar induction using a constituent-context model (2002)

Dan Klein, Christopher D. Manning

This paper presents a novel approach to the unsupervised learning of syntactic analyses of natural language text. Most previous work has focused on maximizing likelihood according to generative PCFG...

LinGO redwoods: A rich and dynamic treebank for HPSG (2002)

Stephan Oepen, Ezra Callahan, Dan Flickinger, Christopher D. Manning, Kristina Toutanova

The LinGO Redwoods initiative is a seed activity in the design and development of a new type of treebank. A treebank is a (typically hand-built) collection of natural language utterances and...

Combining heterogeneous classifiers for word-sense disambiguation (2002)

Dan Klein, Kristina Toutanova, H. Tolga Ilhan, Ar D. Kamvar, Christopher D. Manning

This paper discusses ensembles of simple but heterogeneous classifiers for word-sense disambiguation, examining the Stanford-CS224N system entered in the SENSEVAL-2 English lexical sample task....

Draft. To appear in Bod, Hay and Jannedy (eds),Probabilistic Linguistics, MIT Press Probabilistic Syntax (2002)

Christopher D. Manning

“Everyone knows that language is variable. ” This is the bald sentence with which Sapir (1921:147) begins his chapter on language as an historical product. He goes on to emphasize how two...

Interpreting and extending classical agglomerative clustering algorithms using a model-based approach (2002)

Sepandar D. Kamvar, Dan Klein, Christopher D. Manning

We present two results which arise from a model-based approach to hierarchical agglomerative clustering. First, we show formally that the common heuristic agglomerative clustering algorithms –...

Natural language grammar induction using a constituent-context model (2002)

Dan Klein, Christopher D. Manning

This paper presents a novel approach to the unsupervised learning of syntactic analyses of natural language text. Most previous work has focused on maximizing likelihood according to generative PCFG...

A Generative Constituent-Context Model for Improved Grammar Induction (2002)

Dan Klein, Christopher D. Manning

We present a generative distributional model for the unsupervised induction of natural language syntax which explicitly models constituent yields and contexts. Parameter

From instance-level constraints to space-level constraints: Making the most of prior knowledge in data clustering (2002)

Dan Klein, Sepandar D. Kamvar, Christopher D. Manning

We present an improved method for clustering in the presence of very limited supervisory information, given as pairwise instance constraints. By allowing instance-level constraints to have spacelevel...

Distributional phrase structure induction (2001)

Dan Klein, Christopher D. Manning

Unsupervised grammar induction systems commonly judge potential constituents on the basis of their effects on the likelihood of the data. Linguistic justifications of constituency, on the other hand,...

Parsing with treebank grammars: Empirical bounds, theoretical models, and the structure of the penn treebank (2001)

Dan Klein, Christopher D. Manning

This paper presents empirical studies and closely corresponding theoretical models of the performance of a chart parser exhaustively parsing the Penn Treebank with the Treebank's own CFG...

Distributional phrase structure induction (2001)

Dan Klein, Christopher D. Manning

Unsupervised grammar induction systems commonly judge potential constituents on the basis of their effects on the likelihood of the data. Linguistic justifications of constituency, on the other hand,...

Parsing and hypergraphs (2001)

Dan Klein, Christopher D. Manning

While symbolic parsers can be viewed as deduction systems, this view is less natural for probabilistic parsers. We present a view of parsing as directed hypergraph analysis which naturally covers...

Parsing And Hypergraphs (2001)

Dan Klein And, Dan Klein, Christopher D. Manning

While symbolic parsers can be viewed as deduction systems, this view is less natural for probabilistic parsers.

Distributional phrase structure induction (2001)

Dan Klein, Christopher D. Manning

Unsupervised grammar induction systems commonly judge potential constituents on the basis of their effects on the likelihood of the data. Linguistic justifications of constituency, on the other hand,...

Parsing and hypergraphs (2001)

Dan Klein, Christopher D. Manning

While symbolic parsers can be viewed as deduction systems, this view is less natural for probabilistic parsers. We present a view of parsing as directed hypergraph analysis which naturally covers...

What's needed for lexical databases? Experiences with Kirrkirr (2001)

Christopher D. Manning

This paper discusses what is required from dictionary databases, and one approach, based on experience with Kirrkirr, a dictionary browser originally developed for Warlpiri, an Indigenous Australian...

Distributional phrase structure induction (2001)

Dan Klein, Christopher D. Manning

Unsupervised grammar induction systems commonly judge potential constituents on the basis of their effects on the likelihood of the data. Linguistic justifications of constituency, on the other hand,...

Kirrkirr: Software for Browsing and Visual Exploration of a Structured Warlpiri Dictionary (2001)

Manning, Christopher D., Jansz, Kevin, Indurkhya, Nitin

This paper presents an overview of the goals, architecture, and usability of Kirrkirr, a Java-based visualization tool for XML dictionaries, currently being used with a dictionary for Warlpiri, an...

Enriching the Knowledge Sources Used in a Maximum Entropy Part-of-Speech Tagger (2000)

Kristina Toutanova, Christopher D. Manning

This paper presents results for a maximum entropy -based part of speech tagger, which achieves superior performance principally by enriching the information sources used for tagging. In particular,...

Complex predicates and information spreading in LFG (1999)

Avery D. Andrews, Christopher D. Manning, Reviewed Gosse Bouma

This book is mainly concerned with the theoretical analysis and consequences of two phenomena which are found in a range of languages, namely complex predicate formation and serial verb...

Dissociations Between Argument Structure And Grammatical Relations (1999)

Christopher D. Manning, Christopher D. Manning, Ivan A. Sag, Ivan A. Sag

This paper is based on part of the contents of a paper delivered at the Tubingen HPSG workshop in June 1995, and distributed as Manning and Sag (1995). However, it excludes many topics included in...

The segmentation problem in morphology learning (1998)

Christopher D. Manning, Leinbach Arguing For

Recently there has been a large literature on various approaches to learning morphology, and the success and cognitive plausibility of different approaches (Rumelhart and McClelland (1986),

Argument Structure, Valence, and Binding Nordic Journal of Linguistics (1998)

Christopher D. Manning, Christopher D. Manning, Ivan A. Sag, Ivan A. Sag

This paper develops within HPSG a model of grammar with two syntactic levels, valence lists and argument structure, at which sentences may have different representations: syntactically ergative and...

The Lexical Integrity of Japanese Causatives (1998)

Christopher D. Manning, Ivan A. Sag, Masayo Iida

This paper has had a long gestation. Initial arguments for a lexicalist treatment of Japanese causatives were gathered in a seminar class run by Ivan Sag in 1990. Participants included Makoto...

Argument Structure, Valence, and Binding (1998)

Christopher Manning And, Christopher D. Manning, Christopher D. Manning, Ivan A. Sag, Ivan A. Sag

Manning, C.D. and Sag, I. A. 1998 Argument Structure, Valence, and Binding Nordic Journal of Linguistics This paper develops within HPSG a model of grammar with two syntactic levels, valence lists...

Dissociations Between Argument Structure And Grammatical Relations (1998)

Christopher D. Manning, Christopher D. Manning, Ivan A. Sag, Ivan A. Sag

This paper is based on part of a talk given at the Tubingen HPSG workshop in June 1995, and distributed as Manning and Sag (1995). However, it excludes much material presented there, which will now...

Probabilistic Parsing Using Left Corner Language Models (1997)

Manning, Christopher D., Carpenter, Bob

We introduce a novel parser based on a probabilistic version of a left-corner parser. The left-corner strategy is attractive because rule probabilities can be conditioned on both top-down goals and...

Romance Complex Predicates: In defence of the right-branching structure (1997)

Christopher D. Manning

this paper why that structure is to be preferred and how there are responses to the points made in Abeill'e and Godard (1994). I hope that this argument will seem convincing. If not, I seek...

Probabilistic Parsing Using Left Corner Language Models (1997)

Christopher D. Manning, Bob Carpenter

We introduce a novel parser based on a probabilistic version of a left-corner parser. The left-corner strategy is attractive because rule probabilities can be conditioned on both top-down goals and...

vous ai c. S (1997)

Christopher D. Manning

Abeillé and Godard (1994) seek to show that the rightward branching analysis of French tense auxiliaries shown in (1b), that I argued for in Manning (1992) and which is widely adopted in general, is...

vous ai c. S (1997)

Christopher D. Manning

Abeillé and Godard (1994) seek to show that the rightward branching analysis of French tense auxiliaries shown in (1b), that I argued for in Manning (1992) and which is widely adopted in general, is...

A Theory of Non-constituent Coordination based on Finite-State Rules (1996)

John T. Maxwell, Christopher D. Manning

this paper we outline such an extension to LFG, which allows new forms of cstructure licensing in the presence of coordinations, together with a mechanism to generate the correct f-structure forms.

A Theory of Non-constituent Coordination based on Finite-State Rules (1996)

John Maxwell, Christopher D. Manning

this paper we outline such an extension to LFG, which allows new forms of cstructure licensing in the presence of coordinations, together with a mechanism to generate the correct f-structure forms.

Romance Complex Predicates: Phrasal and Functional Structure (1996)

Christopher D. Manning

this paper I want to (i) present some of the relevant data, (ii) discuss the outlines of LFG approaches to the data, (iii) make some comparisons with corresponding work in HPSG, and (iv) look...

Ergativity: Argument Structure and Grammatical Relations (1995)

Christopher D. Manning

This paper is drawn from my 1994 Stanford dissertation of the same name (copies of which are available from http://kinks.phil.cmu.edu/manning/papers/, or by contacting the author), which should be...

Dissociations Between Argument Structure And Grammatical Relations (1995)

Christopher Manning And, Christopher D. Manning, Christopher D. Manning, Ivan A. Sag, Ivan A. Sag

This paper is based on part of a talk given at the Tubingen HPSG workshop in June 1995, and distributed as Manning and Sag (1995). However, it excludes much material presented there, which will now...

The Lexical Integrity of Japanese Causatives (1994)

Masayo Iida, Christopher D. Manning, Patrick O'Neill, Ivan A. Sag

this paper, we sketch a strictly lexical theory of Japanese causatives that deals with the evidence offered for a complex phrasal analysis. The conclusions we will reach are given in (1) on the...

Automatic Acquisition Of A Large Subcategorization Dictionary From Corpora (1993)

Christopher D. Manning

This paper presents a new method for producing a dictionary of subcategorization frames from unlabelled text corpora. It is shown that statistical filtering of the results of a finite state parser...

Analyzing the verbal noun: Internal and external constraints (1993)

Christopher D. Manning

this paper. First and foremost should be mentioned Peter Sells and Masayo Iida upon whose work this paper builds. I have also received advice and comments (relating to data or linguistic analyses,...

Information Spreading and Levels of Representation in LFG (1993)

Avery D. Andrews, Christopher D. Manning, John Maxwell, Ivan Sag

this paper we will only propose them for universal principles, though there are some intriguing possibilities for language-particular application as well. But to make serious proposals along these...

Romance is so complex (1992)

Christopher D. Manning

In this paper I want to look at what the evidence from Complex Predicates can tell us about the design parameters of an empirically adequate theory of Universal Grammar (UG). This is a fertile field...

Romance is so complex (1992)

Christopher D. Manning

In this paper I want to look at what the evidence from Complex Predicates can tell us about the design parameters of an empirically adequate theory of Universal Grammar (UG). This is a fertile field...

LFG within King's descriptive formalism (1991)

Christopher D. Manning

this paper, I will discuss how Lexical Functional Grammar (LFG: Bresnan, 1982a, etc.) can be modeled in King's (forthcoming) descriptive formalism. This paper isn't an introduction to LFG....

Rethinking Text Segmentation Models: An Information Extraction Case Study

Christopher D. Manning

I examine the use of text segmentation methods on semi-structured text within an information extraction application, arguing that: hierarchical models of discourse structure are necessary, that...

Feature-Rich Part-of-Speech Tagging with a Cyclic Dependency Network

Kristina Toutanova Dan, Dan Klein, Christopher D. Manning, Yoram Singer

We present a new part-of-speech tagger that demonstrates the following ideas: (i) explicit use of both preceding and following tag contexts via a dependency network representation, (ii) broad use of...

Foundations of Statistical Natural Language Processing

Christopher Manning And, Christopher D. Manning, Hinrich Sch Utze, Ma The, Mit Press, Lillian Lee

this paper as "the first clear demonstration of a probabilistic parser outperforming a trigram model" (pg. 457), it does not discuss what features of the algorithm lead to its superior...