A Novel Discriminative Framework for Sentence-Level Discourse Analysis
Published 12 July 2012
Shafiq Joty, Giuseppe Carenini, Raymond T. Ng
Citations76
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
This work proposes a complete probabilistic discriminative framework for performing sentence-level discourse analysis that outperforms the state-of-the-art, often by a wide margin.
Abstract
We propose a complete probabilistic discrim-inative framework for performing sentence-level discourse analysis. Our framework com-prises a discourse segmenter, based on a bi-nary classifier, and a discourse parser, which applies an optimal CKY-like parsing algo-rithm to probabilities inferred from a Dynamic Conditional Random Field. We show on two corpora that our approach outperforms the state-of-the-art, often by a wide margin. 1
Keywords
Computer Science
ScholarlyCommons (University of Pennsylvania)Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data
12,978 Citations2001John Lafferty, Andrew McCallum +1 more
This work presents iterative parameter estimation algorithms for conditional random fields and compares the performance of the resulting models to HMMs and MEMMs on synthetic and natural-language data.
Machine learning: a probabilistic perspective
9,297 Citations2012Kevin P. Murphy
Building a Large Annotated Corpus of English: The Penn Treebank
7,528 Citations1993Mitchell P. Marcus
Computational LinguisticsHead-Driven Statistical Models for Natural Language Parsing
1,860 Citations2003Michael Collins
Three statistical models for natural language parsing are described, leading to approaches in which a parse tree is represented as the sequence of decisions corresponding to a head-centered, top-down derivation of the tree.
A maximum-entropy-inspired parser
1,496 Citations2000Eugene Charniak
A new parser for parsing down to Penn tree-bank style parse trees that achieves 90.1% average precision/recall for sentences of length 40 and less and 89.5% when trained and tested on the previously established sections of the Wall Street Journal treebank is presented.
ArXiv.orgFrustratingly Easy Domain Adaptation
1,395 Citations2009Hal Daumé
This work describes an approach to domain adaptation that is appropriate exactly in the case when one has enough “target” data to do slightly better than just using only “source’ data.
Shallow parsing with conditional random fields
1,251 Citations2003Fei Sha, Fernando Pereira
This work shows how to train a conditional random field to achieve performance as good as any reported base noun-phrase chunking method on the CoNLL task, and better than any reported single model.
The Penn Discourse TreeBank 2.0.
1,130 Citations2008Rashmi Prasad, Nikhil Dinesh +5 more
The second version of the Penn Discourse Treebank, PDTB-2.0, is presented, describing its lexically-grounded annotations of discourse relations and their two abstract object arguments over the 1 million word Wall Street Journal corpus.
Coarse-to-fine <i>n</i>-best parsing and MaxEnt discriminative reranking
888 Citations2005Eugene Charniak, Mark Johnson
This paper describes a simple yet novel method for constructing sets of 50- best parses based on a coarse-to-fine generative parser that generates 50-best lists that are of substantially higher quality than previously obtainable.
The MIT Press eBooksThe Theory and Practice of Discourse Parsing and Summarization
629 Citations2000Daniel Marcu
This book documents the first serious attempt to construct automatically and use nonsemantic computational structures for text summarization and develops a semantics-free theoretical framework that is both general enough to be applicable to naturally occurring texts and concise enough to facilitate an algorithmic approach to discourse analysis.
Statistical decision-tree models for parsing
533 Citations1995David M. Magerman
SPATTER is described, a statistical parser based on decision-tree learning techniques which constructs a complete parse for every sentence and achieves accuracy rates far better than any published result.
Sentence level discourse parsing using syntactic and lexical information
411 Citations2003Radu Soricut, Daniel Marcu
Two probabilistic models that can be used to identify elementary discourse units and build sentence-level discourse parse trees are introduced and shown to be sophisticated enough to yield discourse trees at an accuracy level that matches near-human levels of performance.
Computational LinguisticsRepresenting Discourse Coherence: A Corpus-Based Study
305 Citations2005Florian Wolf, Edward Gibson
A method for annotating discourse coherence structures that was used to manually annotate a database of 135 texts from the Wall Street Journal and the AP Newswire and found many different kinds of crossed dependencies, as well as many nodes with multiple parents.
Edinburgh Research Explorer (University of Edinburgh)Dynamic Conditional Random Fields: Factorized Probabilistic Models for Labeling and Segmenting Sequence Data
292 Citations2007Charles Sutton, Andrew McCallum +1 more
On a natural-language chunking task, it is shown that a DCRF performs better than a series of linear-chain CRFs, achieving comparable performance using only half the training data.
Discourse ProcessesUsing linguistic phenomena to motivate a set of coherence relations
270 Citations1994Alistair Knott, Robert Dale
Computational LinguisticsThe Rhetorical Parsing of Unrestricted Texts: A Surface-based Approach
221 Citations2000Daniel Marcu
This paper explores the extent to which well-formed rhetorical structures can be automatically derived by means of surface-form-based algorithms and shows that automatically derived rhetorical structure trees can be successfully exploited in the context of text summarization.
Dialogue & DiscourseHILDA: A Discourse Parser Using Support Vector Machine Classification
212 Citations2010Hugo Hernault, Helmut Prendinger +2 more
This article presents HILDA, an implemented discourse parser based on RST and Support Vector Machine (SVM) classification that outperforms other discourse parsers for tree structure construction and discourse relation labeling.
Efficient, Feature-based, Conditional Random Field Parsing
180 Citations2008Jenny Rose Finkel, Alex Kleeman +1 more
This work presents the first general, featurerich discriminative parser, based on a conditional random field model, which has been successfully scaled to the full WSJ parsing data, and achieves state-of-the-art results.
Discourse chunking and its application to sentence compression
122 Citations2005Caroline Sporleder, Mirella Lapata
This paper introduces discourse chunking (i.e., the identification of intra-sentential nucleus and satellite spans) as an alternative to full-scale discourse parsing as well as exploiting knowledge-lean features and small amounts of discourse annotations.
An effective discourse parser that uses rich linguistic information
116 Citations2009Rajen Subba, Barbara Di Eugenio
The modified shift-reduce parsing model that uses the authors' relation classifier significantly outperforms a right-branching majority-class baseline and a statistically significant improvement in classifying relations over attribute-value learning paradigms such as Decision Trees, RIPPER and Naive Bayes.
A novel discourse parser based on support vector machine classification
101 Citations2009David A. duVerle, Helmut Prendinger
A new algorithm to parse discourse within the framework of Rhetorical Structure Theory (RST) and a rich feature space is introduced, which is 5% to 12% more accurate than current state-of-the-art parsers.
Synthesis lectures on human language technologiesDiscourse Processing
82 Citations2011Manfred Stede
This work first explores some ways of assigning structure on the document level: the logical document structure as determined by the layout of the text, its genre-specific content structure, and its breakdown into topical segments, then the focus moves to phenomena of local coherence.
Evaluating discourse-based answer extraction for <i>why</i> -question answering
64 Citations2007Suzan Verberne, Lou Boves +2 more
Tree-based reparameterization for approximate inference on loopy graphs
62 Citations2001Martin J. Wainwright, Tommi Jaakkola +1 more
A tree-based reparameterization framework that provides a new conceptual view of a large class of iterative algorithms for computing approximate marginals in graphs with cycles, which includes belief propagation, which can be reformulated as a very local form of reparametersization.
Domain adaptation of natural language processing systems
60 Citations2008Fernando Pereira, John Blitzer
A measure of divergence is described, the HDH -divergence, that depends on the hypothesis class H from which the supervised model H is estimated, that is used to state an upper bound on the true target error of a model trained to minimize a convex combination of empirical source and target errors.
International Journal of Semantic ComputingIDENTIFYING JUSTIFICATIONS IN WRITTEN DIALOGS BY CLASSIFYING TEXT AS ARGUMENTATIVE
55 Citations2011Or Biran, Owen Rambow
A method to detect the existence of certain types of discourse relations, which helps to classify whether a segment is a justification or not is developed, which uses a large set of connectives, which are called indicators.
The utility of parse-derived features for automatic discourse segmentation
54 Citations2007Seeger Fisher, Brian Roark
It is demonstrated that the SPADE-inspired context-free features are critical to achieving this level of accuracy on this task, and counters recent results suggesting that purely finite-state approaches can perform competitively.
Institutional Research Information System (Università degli Studi di Trento)Shallow Discourse Parsing with Conditional Random Fields
52 Citations2011Sucheta Ghosh, Richard Johansson +2 more
This paper takes a data driven approach to identify arguments of explicit discourse connectives and designs the argument segmentation task as a cascade of decisions based on conditional random fields (CRFs).
Natural Language EngineeringRobust discourse parsing via discourse markers, topicality and position
46 Citations2002Frank Schilder
Results from a psycholinguistic experiment, indicating the most salient sentences for a given text as the ‘gold standard’, show that the proposed algorithm performs better than commonly used machine learning and statistical approaches to summarisation.
HeliyonThe Penn Discourse TreeBank as a Resource for Natural Language Generation
39 Citations2005Rashmi Prasad, Aravind K. Joshi +4 more
Discourse-level relations for opinion analysis
35 Citations2010Janyce Wiebe, Swapna Somasundaran
This thesis proposes a new linguistic representational scheme designed to support interdependent interpretations of opinions in the discourse, and adapt and extend an existing subjectivity annotation scheme to capture discourse-level relations in a multi-party meeting corpus.