Large Margin Synchronous Generation and its Application to Sentence Compression
Edinburgh Research Explorer (University of Edinburgh)Published 1 June 2007Open access
Trevor Cohn, Mirella Lapata
Citations39
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 paper presents a tree-to-tree transduction method for text rewriting based on synchronous tree substitution grammar, a formalism that allows local distortion of the tree topology and can naturally capture structural mismatches.
Abstract
This paper presents a tree-to-tree transduction method for text rewriting. Our model is based on synchronous tree substitution grammar, a formalism that allows local distortion of the tree topology and can thus naturally capture structural mismatches. We describe an algorithm for decoding in this framework and show how the model can be trained discriminatively within a large margin framework. Experimental results on sentence compression bring significant improvements over a state-of-the-art model. 1
Keywords
Computer Science
MPG.PuRe (Max Planck Society)Large Margin Methods for Structured and Interdependent Output Variables
1,952 Citations2005Ioannis Tsochantaridis, Thorsten Joachims +2 more
This paper proposes to appropriately generalize the well-known notion of a separation margin and derive a corresponding maximum-margin formulation and presents a cutting plane algorithm that solves the optimization problem in polynomial time for a large class of problems.
A hierarchical phrase-based model for statistical machine translation
1,161 Citations2005David Chiang
The model is formally a synchronous context-free grammar but is learned from a bitext without any syntactic information, which can be seen as a shift to the formal machinery of syntax-based translation systems without any linguistic commitment.
Computational LinguisticsThe Alignment Template Approach to Statistical Machine Translation
933 Citations2004Franz Josef Och, Hermann Ney
A phrase-based statistical machine translation approach the alignment template approach is described, which allows for general many-to-many relations between words and is easier to extend than classical statistical machinetranslation systems.
A support vector method for multivariate performance measures
800 Citations2005Thorsten Joachims
An algorithm with which such multivariate SVMs can be trained in polynomial time for large classes of potentially non-linear performance measures, in particular ROCArea and all measures that can be computed from the contingency table are given.
arXiv (Cornell University)Learning to Map Sentences to Logical Form: Structured Classification with Probabilistic Categorial Grammars
791 Citations2012Luke Zettlemoyer, Michael J. Collins
Natural Language EngineeringDiscovery of inference rules for question-answering
532 Citations2001Dekang Lin, Patrick Pantel
This paper presents an unsupervised algorithm for discovering inference rules from text based on an extended version of Harris’ Distributional Hypothesis, which states that words that occurred in the same contexts tend to be similar.
Artificial IntelligenceSummarization beyond sentence extraction: A probabilistic approach to sentence compression
490 Citations2002Kevin Knight, Daniel Marcu
This paper focuses on sentence compression, a simpler version of this larger challenge, and aims to achieve two goals simultaneously: the authors' compressions should be grammatical, and they should retain the most important pieces of information.
RWTH Publications (RWTH Aachen)Improved Alignment Models for Statistical Machine Translation
482 Citations1999Franz Josef Och, Christoph Tillmann +1 more
Improved alignment models for statistical machine translation are described and experimental results are presented using the Verbmobil task (German-English, 6000word vocabulary) which is a limited-domain spoken-language task.
Extracting paraphrases from a parallel corpus
480 Citations2001Regina Barzilay, Kathleen McKeown
This work presents an unsupervised learning algorithm for identification of paraphrases from a corpus of multiple English translations of the same source text that yields phrasal and single word lexical paraphrasing as well as syntactic paraphrase.
Monolingual Machine Translation for Paraphrase Generation
321 Citations2004Chris Quirk, Chris Brockett +1 more
Human evaluation shows that this SMT system outperforms baseline paraphrase generation techniques and, in a departure from previous work, offers better coverage and scalability than the current best-of-breed paraphrasing approaches.
Sentence reduction for automatic text summarization
284 Citations2000Hongyan Jing
A novel sentence reduction system for automatically removing extraneous phrases from sentences that are extracted from a document for summarization purpose using multiple sources of knowledge, including syntactic knowledge, context information, and statistics computed from a corpus which consists of examples written by human professionals.
Learning non-isomorphic tree mappings for machine translation
243 Citations2003Jason Eisner
This work reformulates synchronous TSG to permit dependency trees, and sketch EM/Viterbi algorithms for alignment, training, and decoding.
Syntax-based alignment of multiple translations
205 Citations2003Bo Pang, Kevin Knight +1 more
A syntax-based algorithm that automatically builds Finite State Automata (word lattices) from semantically equivalent translation sets that are good representations of paraphrases and can predict the correctness of alternative semantic renderings, which may be used to evaluate the quality of translations.
Automatic paraphrase acquisition from news articles
178 Citations2002Yusuke Shinyama, Satoshi Sekine +1 more
This is the initial attempt at automatically extracting paraphrases from a corpus, and the results are promising.
Supervised and unsupervised learning for sentence compression
156 Citations2005Jenine Turner, Eugene Charniak
In addition to improving the original K&M noisy-channel model, unsupervised and semi-supervised models of the task are created to point out problems with modeling the task in this way.
Conference of the European Chapter of the Association for Computational LinguisticsSimplifying Text for Language-Impaired Readers.
156 Citations1999John Carroll, Guido Minnen +4 more
A case of a 12-year-old boy with Kimura disease who had a history of repeated severe influenza virus A infection is presented, and enzyme-linked immunospot assay showed elevated numbers of IL-5- and IL-10-producing cells in the peripheral blood.
Computational LinguisticsTraining Tree Transducers
139 Citations2008Jonathan Graehl, Kevin Knight +1 more
This work motivates the use of tree transducers for natural language and addresses the training problem for probabilistic tree- to-tree and tree-to-string transducers.
Design of a multi-lingual, parallel-processing statistical parsing engine
132 Citations2002Daniel M. Bikel
Ever since the widespread availability of the Penn Treebank, there have been numerous, statistical parsers developed for English, e.g. [8], but to varying degrees these parsers and others---while very successful at the tasks for which they were designed---had the following limitations.
Statistical machine translation by parsing
117 Citations2004I. Dan Melamed
This paper explores generalizations of ordinary parsing algorithms that allow the input to consist of string tuples and/or the grammar to range over string tuples that can infer the synchronous structures hidden in parallel texts.
Lexicalized Markov Grammars for Sentence Compression
104 Citations2007Kathleen McKeown, Michel Galley
A headdriven Markovization formulation of SCFG deletion rules is defined, which allows us to lexicalize probabilities of constituent deletions, and a robust approach for tree-to-tree alignment between arbitrary document-abstract parallel corpora is used.
Models for sentence compression
103 Citations2006James Clarke, Mirella Lapata
This paper provides a novel comparison between a supervised constituent-based and an weakly supervised word-based compression algorithm and examines how these models port to different domains (written vs. spoken text).
Statistical sentence condensation using ambiguity packing and stochastic disambiguation methods for Lexical-Functional Grammar
79 Citations2003Stefan Riezler, Tracy Holloway King +2 more
Overall summarization quality of the proposed system is state-of-the-art, with guaranteed grammaticality of the system output due to the use of a constraint-based parser/generator.
Constraint-based sentence compression an integer programming approach
70 Citations2006James Clarke, Mirella Lapata
This work develops an integer programming formulation and infer globally optimal compressions in the face of linguistically motivated constraints and shows that such a formulation allows for relatively simple and knowledge-lean compression models that do not require parallel corpora or large-scale resources.
Edinburgh Research Explorer (University of Edinburgh)Modelling Compression with Discourse Constraints
69 Citations2007James Clarke, Mirella Lapata
A discourse informed model which is capable of producing document compressions that are coherent and informative is presented, inspired by theories of local coherence and formulated within the framework of Integer Linear Programming.
Tokyo Tech Research Repository (Tokyo Institute of Technology)Speech Summarization: An Approach through Word Extraction and a Method for Evaluation ∗
55 Citations2004Chiori Hori, Sadaoki Furui
Japanese broadcast-news speech, transcribed using a large-vocabulary continuous-speech recognition (LVCSR) system, is summarized and evaluated using the proposed method with 20, 40, 60, 70 and 80% summarization ratios.