Paraphrasing and textual entailment recognition and generation
Published 1 January 2011Open access
Πρόδρομος Μαλακασιώτης
Citations6
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.
Abstract
Οι μέθοδοι παραφράσεων αναγνωρίζουν, παράγουν ή εξάγουν φράσεις προτάσεις οι μεγαλύτερες γλωσσικές εκφράσεις που περιέχουν περίπου την ίδια περίπου πληροφορία. Αντίθετα, οι μέθοδοι κειμενικής συνεπαγωγής αναγνωρίζουν, παράγουν ή εξάγουν ζεύγη γλωσσικών εκφράσεων, τέτοια ώστε ένας άνθρωπος ο οποίος διαβάζει (και εμπιστεύεται) το πρώτο μέλος του ζεύγους είναι πολύ πιθανό να συμπεράνει ότι και το δεύτερο μέλος του ζεύγους είναι αληθές. Οι παραφράσεις μπορούν να θεωρηθούν περιπτώσεις αμφίδρομης κειμενικής συνεπαγωγής και οι μέθοδοι που χρησιμοποιούνται στις δύο περιοχές είναι συχνά παρόμοιες. Και τα δύο είδη μεθόδων είναι χρήσιμα σε πολλές εφαρμογές επεξεργασίας φυσικής γλώσσας, όπως συστήματα ερωταποκρίσεων, παραγωγή φυσικής γλώσσα, παραγωγή περιλήψεων και μηχανική μετάφραση. Στην παρούσα διατριβή, επικεντρωνόμαστε στην αναγνώριση παραφράσεων και κειμενικής συνεπαγωγής, καθώς και στην παραγωγή παραφράσεων. Προτείνουμε τρεις μεθόδους αναγνώρισης παραφράσεων και κειμενικής συνεπαγωγής τις οποίες αξιολογούμε σε καθιερωμένα σύνολα δεδομένων. Η βασική ιδέα είναι ότι αναγνωρίζοντας ομοιότητα σε διάφορες παραλλαγές των γλωσσικών εκφράσεων, μπορούμε να αναγνωρίσουμε παραφράσεις και κειμενική συνεπαγωγή σε ικανοποιητικό βαθμό. Επιπλέον, χρησιμοποιούμε το WordNet καθώς και επιπλέον χαρακτηριστικά που ενεργούν στο συντακτικό επίπεδο των γλωσσικών εκφράσεων. Η καλύτερη από τις τρεις μεθόδους αναγνώρισης που προτείνουμε επιτυγχάνει τα καλύτερα αποτελέσματα στο ευρέως χρησιμοποιούμενο σώμα παραφράσεων MSR, ενώ και η απλούστερη από τις μεθόδους είναι ιδιαίτερα ανταγωνιστική. Όσον αφορά την κειμενική συνεπαγωγή οι μέθοδοί μας επιτυγχάνουν χειρότερα αποτελέσματα. Εν τούτοις, οι επιδόσεις τους είναι αρκετά καλές παρά το γεγονός ότι είναι απλούστερες από άλλες μεθόδους? συνεπώς μπορούν να θεωρηθούν ως ανταγωνιστικά βασικά συστήματα για μελλοντική έρευνα...
Keywords
Computer Science
TechnometricsStatistical Learning Theory
26,913 Citations1999Yuhai Wu, Vladimir Vapnik
Presenting a method for determining the necessary and sufficient conditions for consistency of learning process, the author covers function estimates from small data pools, applying these estimations to real-life problems, and much more.
C4.5: Programs for Machine Learning
23,665 Citations1992J. R. Quinlan
A complete guide to the C4.5 system as implemented in C for the UNIX environment, which starts from simple core learning methods and shows how they can be elaborated and extended to deal with typical problems such as missing data and over hitting.
Journal of Computer and System SciencesA Decision-Theoretic Generalization of On-Line Learning and an Application to Boosting
20,320 Citations1997Yoav Freund, Robert E. Schapire
Cambridge University Press eBooksAn Introduction to Support Vector Machines and Other Kernel-based Learning Methods
13,883 Citations2000Nello Cristianini, John Shawe‐Taylor
Language<b>WordNet: An electronic lexical database</b> . Ed. by Christiane Fellbaum. Cambridge, MA: MIT Press, 1998. Pp. xxii, 423.
11,687 Citations2000Adam Kilgarriff
The lexical database: nouns in WordNet, George A. Miller modifiers in WordNet, Katherine J. Miller a semantic network of English verbs, and applications of WordNet: building semantic concordances are presented.
Modern Information Retrieval
11,544 Citations1999Ricardo Baeza‐Yates, Berthier Ribeiro‐Neto
Foundations of statistical natural language processing
9,996 Citations1999Christopher D. Manning, Hinrich Schütze
Program electronic library and information systemsAn algorithm for suffix stripping
8,136 Citations1980Martin Porter
An algorithm for suffix stripping is described, which has been implemented as a short, fast program in BCPL, and performs slightly better than a much more elaborate system with which it has been compared.
The Annals of StatisticsAdditive logistic regression: a statistical view of boosting (With discussion and a rejoinder by the authors)
6,842 Citations2000Jerome H. Friedman, Trevor Hastie +1 more
This work shows that this seemingly mysterious phenomenon of boosting can be understood in terms of well-known statistical principles, namely additive modeling and maximum likelihood, and develops more direct approximations and shows that they exhibit nearly identical results to boosting.
The mathematics of statistical machine translation: parameter estimation
4,125 Citations1993Peter F. Brown, Vincent J. Della Pietra +2 more
It is reasonable to argue that word-by-word alignments are inherent in any sufficiently large bilingual corpus, given a set of pairs of sentences that are translations of one another.
Computational LinguisticsA Systematic Comparison of Various Statistical Alignment Models
3,928 Citations2003Franz Josef Och, Hermann Ney
An important result is that refined alignment models with a first-order dependence and a fertility model yield significantly better results than simple heuristic models.
An Information-Theoretic Definition of Similarity
3,662 Citations1998Dekang Lin
This work presents an informationtheoretic definition of similarity that is applicable as long as there is a probabilistic model and demonstrates how this definition can be used to measure the similarity in a number of different domains.
Speech and language processing
3,589 Citations2010Dan Jurafsky, James Martin +1 more
It is now clear that HAL’s creator, Arthur C. Clarke, was a little optimistic in predicting when an artificial agent such as HAL would be avail-able.
Statistical phrase-based translation
3,268 Citations2003Philipp Koehn, Franz Josef Och +1 more
The empirical results suggest that the highest levels of performance can be obtained through relatively simple means: heuristic learning of phrase translations from word-based alignments and lexical weighting of phrase translation.
Accurate unlexicalized parsing
3,055 Citations2003Dan Klein, Christopher D. Manning
It is demonstrated 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 assumptions latent in a vanilla treebank grammar.
Distant supervision for relation extraction without labeled data
2,913 Citations2009Mike D. Mintz, Steven Bills +2 more
This work investigates an alternative paradigm that does not require labeled corpora, avoiding the domain dependence of ACE-style algorithms, and allowing the use of corpora of any size.
The Berkeley FrameNet Project
2,564 Citations1998Collin F. Baker, Charles J. Fillmore +1 more
This report will present the project's goals and workflow, and information about the computational tools that have been adapted or created in-house for this work.
arXiv (Cornell University)Assessing agreement on classification tasks: the kappa statistic
2,092 Citations1996Jean Carletta
Journal of Artificial Intelligence ResearchSemantic Similarity in a Taxonomy: An Information-Based Measure and its Application to Problems of Ambiguity in Natural Language
2,085 Citations1999Philip Resnik
This article presents a measure of semantic similarity in an IS-A taxonomy based on the notion of shared information content that performs better than the traditional edge-counting approach.
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.
Series in machine perception and artificial intelligenceIntroduction to Machine Learning
1,654 Citations2019
Introduction to Machine Learning is a comprehensive textbook on the subject, covering a broad array of topics not usually included in introductory machine learning texts, and discusses many methods from different fields, including statistics, pattern recognition, neural networks, artificial intelligence, signal processing, control, and data mining.
Lecture notes in computer scienceThe PASCAL Recognising Textual Entailment Challenge
1,626 Citations2006Ido Dagan, Oren Glickman +1 more
Automatic retrieval and clustering of similar words
1,555 Citations1998Dekang Lin
A word similarity measure based on the distributional pattern of words allows the automatically constructed thesaurus to be significantly closer to WordNet than Roget Thesaurus is.
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.
A simple rule-based part of speech tagger
1,418 Citations1992Eric Brill
This work presents a simple rule-based part of speech tagger which automatically acquires its rules and tags with accuracy comparable to stochastic taggers, demonstrating that the stochastics method is not the only viable method for part ofspeech tagging.
Computational LinguisticsEvaluating WordNet-based Measures of Lexical Semantic Relatedness
1,414 Citations2006Alexander Budanitsky, Graeme Hirst
An information-content-based measure proposed by Jiang and Conrath is found superior to those proposed by Hirst and St-Onge, Leacock and Chodorow, Lin, and Resnik, and why distributional similarity is not an adequate proxy for lexical semantic relatedness.
Learning to Classify Text Using Support Vector Machines
1,366 Citations2002Thorsten Joachims
This book gives a concise introduction to SVMs for pattern recognition, and it includes a detailed description of how to formulate text-classification tasks for machine learning.
SIAM Journal on ComputingSimple Fast Algorithms for the Editing Distance between Trees and Related Problems
1,275 Citations1989Kaizhong Zhang, Dennis Shasha
Algorithms are designed to answer the following kinds of questions about trees: what is the distance between two trees, and the analogous question for prunings as for subtrees.
BioinformaticsBiological sequence analysis
1,251 Citations2021Samvedna Shukla, Bhawana Mishra +2 more
The basics of sequence alignment, algorithms, and tools available for biological sequence alignment are discussed, which has important application in disease diagnosis, biomaterial engineering, genetic engineering, and drug discovery.
arXiv (Cornell University)Building Natural-Language Generation Systems
1,249 Citations1996Ehud Reiter
Automatically Constructing a Corpus of Sentential Paraphrases.
1,114 Citations2005William B. Dolan, Chris Brockett
The creation of the recently-released Microsoft Research Paraphrase Corpus, which contains 5801 sentence pairs, each hand-labeled with a binary judgment as to whether the pair constitutes a paraphrase, is described.
A program for aligning sentences in bilingual corpora
956 Citations1993William A. Gale, Kenneth Church
This paper will describe a method and a program for aligning sentences based on a simple statistical model of character lengths, which uses the fact that longer sentences in one language tend to be translated into longer sentence in the other language, and that shorter sentences tend to been translated into shorter sentences.
Learning to Classify Text Using Support Vector Machines: Methods, Theory and Algorithms
934 Citations2002Thorsten Joachims
Journal of the ACMThe Tree-to-Tree Correction Problem
856 Citations1979Kuo‐Chung Tai
An algorithm is presented which solves the problem of determining the distance from T to T' as measured by the mlmmum cost sequence of edit operaUons needed to transform T into T'.
Zenodo (CERN European Organization for Nuclear Research)VerbNet: A broad-coverage, comprehensive verb lexicon
845 Citations2005Karin Kipper Schuler
VerbNet is created, a verb lexicon compatible with Word-Net but with explicitly stated syntactic and semantic information, using Levin verb classes to systematically construct lexical entries, to address the gap in coverage of syntactic frames and predicate argument structures associated with individual verb senses.
Natural language processingAutomatic Summarization
839 Citations2001Inderjeet Mani
The challenges that remain open, in particular the need for language generation and deeper semantic understanding of language that would be necessary for future advances in the field are discussed.
The State of Record Linkage and Current Research Problems
817 Citations1999William E. Winkler
This paper provides an overview of methods and systems developed for record linkage based on the formal mathematical model of Fellegi and Sunter, and highlights the work of Larsen and Rubin.
Learning surface text patterns for a Question Answering system
813 Citations2001Deepak Ravichandran, Eduard Hovy
This paper has developed a method for learning an optimal set of surface text patterns automatically from a tagged corpus, and calculates the precision of each pattern, and the average precision for each question type.
Natural Language EngineeringMaltParser: A language-independent system for data-driven dependency parsing
805 Citations2007Joakim Nivre, Johan Hall +6 more
Experimental evaluation confirms that MaltParser can achieve robust, efficient and accurate parsing for a wide range of languages without language-specific enhancements and with rather limited amounts of training data.
Statistics in MedicineProbabilistic linkage of large public health data files
787 Citations1995Matthew A. Jaro
Probabilistic linkage technology makes it feasible and efficient to link large public health databases in a statistically justifiable manner by linking highway crashes to Emergency Medical Service reports and to hospital admission records for the National Highway Traffic Safety Administration (NHTSA).
Machine LearningAn Algorithm that Learns What's in a Name
784 Citations1999Daniel M. Bikel, Richard Schwartz +1 more
IdentiFinderTM, a hidden Markov model that learns to recognize and classify names, dates, times, and numerical quantities, is evaluated and is competitive with approaches based on handcrafted rules on mixed case text and superior on text where case information is not available.
Less is More: Active Learning with Support Vector Machines
775 Citations2000Greg Schohn, David Cohn
A simple active learning heuristic is described which greatly enhances the generalization behavior of support vector machines (SVMs) on several practical document classification tasks and frequently does so in less time than the naive approach of training on all available data.
Computational LinguisticsAn algorithm for pronominal anaphora resolution
758 Citations1994Shalom Lappin, Herbert J. Leass
The algorithm applies to the syntactic representations generated by McCord's Slot Grammar parser and relies on salience measures derived from syntactic structure and a simple dynamic model of attentional state and to models of anaphora resolution that invoke a variety of informational factors in ranking antecedent candidates.
Natural Language EngineeringNatural language interfaces to databases – an introduction
741 Citations1995Ion Androutsopoulos, Graéme Ritchie +1 more
An introduction to natural language interfaces to databases (NLIDBS) and some less explored areas of NLIDB research are presented, namely database updates, meta-knowledge questions, temporal questions, and multi-modal NLIDBS.
Unsupervised construction of large paraphrase corpora
740 Citations2004Bill Dolan, Chris Quirk +1 more
Investigation of unsupervised techniques for acquiring monolingual sentence-level paraphrases from a corpus of temporally and topically clustered news articles collected from thousands of web-based news sources shows that edit distance data is cleaner and more easily-aligned than the heuristic data.
Learning dictionaries for information extraction by multi-level bootstrapping
688 Citations1999Ellen Riloff, Rosie Jones
A multilevel bootstrapping algorithm is presented that generates both the semantic lexicon and extraction patterns simultaneously simultaneously and produces high-quality dictionaries for several semantic categories.
Lecture notes in computer sciencePharaoh: A Beam Search Decoder for Phrase-Based Statistical Machine Translation Models
634 Citations2004Philipp Koehn
Pharaoh, a freely available decoder for phrase-based statistical machine translation models is described, which is the implement at ion of an efficient dynamic programming search algorithm with lattice generation and XML markup for external components.
Re-evaluating the Role of Bleu in Machine Translation Research
621 Citations2006Chris Callison-Burch, Miles Osborne +1 more
It is shown that an improved Bleu score is neither necessary nor sufficient for achieving an actual improvement in translation quality, and two significant counterexamples to Bleu’s correlation with human judgments of quality are given.
Automatically generating extraction patterns from untagged text
620 Citations1996Ellen Riloff
This work has developed a system called AutoSlog-TS that creates dictionaries of extraction patterns using only untagged text, and in experiments with the MUG-4 terrorism domain, created a dictionary of extraction pattern that performed comparably to a dictionary created by autoSlog, using only preclassified texts as input.
LinguaResolving pronoun references
615 Citations1978Jerry R. Hobbs
It is shown in a detailed treatment of several examples how semantic analysis locates the antecedents of most pronouns as a by-product in a comprehensive system for semantic analysis of English texts.
The Seventh PASCAL Recognizing Textual Entailment Challenge.
578 Citations2008Luisa Bentivogli, Peter E. Clark +2 more
This paper presents the Seventh Recognizing Textual Entailment (RTE-7) challenge, which replicated the exercise proposed in RTE-6, consisting of a Main Task, a Main subtask aimed at detecting novel information; and a KBP Validation Task, in which RTE systems had to validate the output of systems participating in the KBP Slot Filling Task.
Paraphrasing with bilingual parallel corpora
547 Citations2005Colin Bannard, Chris Callison-Burch
This work defines a paraphrase probability that allows paraphrases extracted from a bilingual parallel corpus to be ranked using translation probabilities, and shows how it can be refined to take contextual information into account.
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.
Computational LinguisticsThe Kappa Statistic: A Second Look
498 Citations2004Barbara Di Eugenio, Michael Glass
This squib discusses the assumptions underlying different computations of the expected agreement component of the kappa coefficient of agreement and discusses how prevalence and bias affect the measure.
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.
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.
Computational LinguisticsSentence Fusion for Multidocument News Summarization
443 Citations2005Regina Barzilay, Kathleen McKeown
This article introduces sentence fusion, a novel text-to-text generation technique for synthesizing common information across documents that moves the summarization field from the use of purely extractive methods to the generation of abstracts that contain sentences not found in any of the input documents and can synthesize information across sources.
Computational LinguisticsUsing corpus statistics and WordNet relations for sense identification
441 Citations1998Claudia Leacock, George A. Miller +1 more
A statistical classifier is described that combines topical context with local cues to identify a word sense and is used to disambiguate a noun, a verb, and an adjective.
Learning to paraphrase
432 Citations2003Regina Barzilay, Lillian Lee
This work applies multiple-sequence alignment to sentences gathered from unannotated comparable corpora: it learns a set of paraphrasing patterns represented by word lattice pairs and automatically determines how to apply these patterns to rewrite new sentences.
Information Processing LettersThe tree-to-tree editing problem
412 Citations1977Stanley M. Selkow
It is shown that a straightforward generalization of the Sankoff algorithm will provide a solution to the tree-to-tree editing problem and it follows that the algorithm must be optimal over a wide class of computation models.
Computational LinguisticsDiscriminative Reranking for Natural Language Parsing
407 Citations2005Michael J. Collins, Terry Koo
The boosting approach to ranking problems described in Freund et al. (1998) is applied to parsing the Wall Street Journal treebank, and it is argued that the method is an appealing alternative-in terms of both simplicity and efficiency-to work on feature selection methods within log-linear (maximum-entropy) models.
The Annals of Mathematical StatisticsMaximum Entropy for Hypothesis Formulation, Especially for Multidimensional Contingency Tables
401 Citations1963I. J. Good
Computational LinguisticsImproving Machine Translation Performance by Exploiting Non-Parallel Corpora
392 Citations2005Dragos Stefan Munteanu, Daniel Marcu
A maximum entropy classifier is trained that, given a pair of sentences, can reliably determine whether or not they are translations of each other and can be applied with great benefit to language pairs for which only scarce resources are available.
Measuring the semantic similarity of texts
352 Citations2005Courtney D. Corley, Rada Mihalcea
A method that combines word- to-word similarity metrics into a text-to-text metric is introduced, and it is shown that this method outperforms the traditional text similarity metrics based on lexical matching.
The MIT Press eBooksAutomated Discovery of WordNet Relations
325 Citations1998Marti A. Hearst
This chapter describes a method for the automatic discovery of WordNetstyle lexico-semantic relations by searching for correspondingLexico-syntactic patterns in large text collections using the Lexico-Syntactic Pattern Extraction (LSPE) method.
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.
Distributional Structure
317 Citations1970Zellig S. Harris
This discussion will discuss how each language can be described in terms of a distributional structure, i.e. in Terms of the occurrence of parts relative to other parts, and how this description is complete without intrusion of other features such as history or meaning.
Journal of Artificial Intelligence ResearchGlobal Inference for Sentence Compression: An Integer Linear Programming Approach
316 Citations2008James Clarke, Mirella Lapata
This work shows how previous formulations of sentence compression can be recast as ILPs and extend these models with novel global constraints to infer globally optimal compressions in the presence of linguistically motivated constraints.
Computational LinguisticsGenerating Phrasal and Sentential Paraphrases: A Survey of Data-Driven Methods
302 Citations2010Nitin Madnani, Bonnie J. Dorr
A comprehensive and application-independent survey of data-driven phrasal and sentential paraphrase generation methods is conducted, while also conveying an appreciation for the importance and potential use of paraphrases in the field of NLP research.
Improved statistical machine translation using paraphrases
295 Citations2006Chris Callison-Burch, Philipp Koehn +1 more
This work shows how techniques from paraphrasing can be used to deal with otherwise unknown source language phrases and shows that augmenting a state-of-the-art SMT system with paraphrases leads to significantly improved coverage and translation quality.
ArXiv.orgCRYSTAL: Inducing a Conceptual Dictionary
273 Citations1995Stephen Soderland, D A Fisher +2 more
Fast decoding and optimal decoding for machine translation
234 Citations2001Ulrich Germann, Michael Jahr +3 more
This paper compares the speed and output quality of a traditional stack-based decoding algorithm with two new decoders: a fast greedy decoder and a slow but optimal decoder that treats decoding as an integer-programming optimization problem.
Methods for using textual entailment in open-domain question answering
232 Citations2006Sanda M. Harabagiu, Andrew Hickl
It is demonstrated how computational systems designed to recognize textual entailment can be used to enhance the accuracy of current open-domain automatic question answering (Q/A) systems.
Finding Contradictions in Text
230 Citations2008Marie-Catherine de Marneffe, Anna N. Rafferty +1 more
It is demonstrated that a system for contradiction needs to make more fine-grained distinctions than the common systems for entailment, and is argued for the centrality of event coreference and therefore incorporate such a component based on topicality.
Extraction Patterns for Information Extraction Tasks: A Survey
227 Citations1999Ion Muslea
This paper surveys the various types of extraction patterns that are generated by machine learning algorithms and identifies three main categories of patterns, which cover a variety of application domains, and compares and contrast the patterns from each category.
Recognising textual entailment with logical inference
226 Citations2005Johan Bos, Katja Markert
This work incorporates model building, a technique borrowed from automated reasoning, and shows that it is a useful robust method to approximate entailment, and uses machine learning to combine these deep semantic analysis techniques with simple shallow word overlap.
Paraphrasing for automatic evaluation
221 Citations2006David Kauchak, Regina Barzilay
It is shown that the use of a paraphrased synthetic reference refines the accuracy of automatic evaluation and there is a strong connection between the quality of automatic paraphrases as judged by humans and their contribution to automatic evaluation.
Statistical Machine Translation for Query Expansion in Answer Retrieval
221 Citations2007Stefan Riezler, Alexander Vasserman +3 more
An approach to query expansion in answer retrieval that uses Statistical Machine Translation (SMT) techniques to bridge the lexical gap between questions and answers is presented.
Paraphrase identification as probabilistic quasi-synchronous recognition
215 Citations2009Dipanjan Das, Noah A. Smith
A generative model is employed that generates a paraphrase of a given sentence, and probabilistic inference is used to reason about whether two sentences share the paraphrase relationship.
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.
Computational LinguisticsQuestion Answering in Restricted Domains: An Overview
201 Citations2007Diego Mollá, José Luis Vicedo González
The article contains a historical perspective on question answering over restricted domains and an overview of the current methods and applications used in restricted domains.
Natural Language EngineeringRecognizing textual entailment: Rational, evaluation and approaches
200 Citations2009Ido Dagan, Bill Dolan +2 more
This special issue of the JNLE provides an opportunity to showcase some of the most important work in this emerging area of textual entailment, particularly automatic acquisition of paraphrases and lexical semantic relationships and unsupervised inference in applications such as question answering, information extraction and summarization.
Sentence alignment for monolingual comparable corpora
195 Citations2003Regina Barzilay, Noémie Elhadad
This work addresses the problem of sentence alignment for monolingual corpora by incorporating context into the search for an optimal alignment in two complementary ways: learning rules for matching paragraphs using topic structure and refining the matching through local alignment to find good sentence pairs.
Information Extraction: Algorithms and Prospects in a Retrieval Context
184 Citations2006Marie‐Francine Moens
Syntactic constraints on paraphrases extracted from parallel corpora
183 Citations2008Chris Callison-Burch
This work improves the quality of paraphrases extracted from parallel corpora by requiring that phrases and their paraphrasing be the same syntactic type and altering the phrase extraction algorithm to extract phrase labels alongside bilingual phrase pairs.
Bitext maps and alignment via pattern recognition
179 Citations1999I. Dan Melamed
This article advances the state of the art of bitext mapping by formulating the problem in terms of pattern recognition and presenting the Smooth Injective Map Recognizer (SIMR) algorithm, which has produced bitext maps for over 200 megabytes of French-English bitexts.
Sentence compression beyond word deletion
178 Citations2008Trevor Cohn, Mirella Lapata
A new corpus that is suited to the sentence compression task is presented and a discriminative tree-to-tree transduction model that can naturally account for structural and lexical mismatches is presented.
Institutional Research Information System (Università degli Studi di Trento)Scaling Web-based Acquisition of Entailment Relations.
172 Citations2004Idan Szpektor, Hristo Tanev +2 more
This work presents a fully unsupervised learning algorithm for Web-based extraction of entailment relations, an extended model of paraphrases, focusing on increased scalability and generality with respect to prior work, eventually aiming at a full scale knowledge base.
Robust textual inference via graph matching
159 Citations2005Aria Haghighi, Andrew Y. Ng +1 more
A learned graph matching approach to approximate entailment using the amount of the sentence's semantic content which is contained in the text, which outperforms Bag-Of-Words and TF-IDF models.
Journal of Artificial Intelligence ResearchSentence Compression as Tree Transduction
157 Citations2009Timothy A. Cohn, Mirella Lapata
This paper presents a tree-to-tree transduction method for sentence compression based on synchronous tree substitution grammar, a formalism that allows local distortion of the tree topology and can naturally capture structural mismatches.
Improved statistical machine translation using monolingually-derived paraphrases
153 Citations2009Yuval Marton, Chris Callison-Burch +1 more
This work presents what is to their knowledge the first successful integration of a collocational approach to untranslated words with an end-to-end, state of the art SMT system demonstrating significant translation improvements in a low-resource setting.
Lecture notes in computer scienceLearning information extraction patterns from examples
146 Citations1996Scott B. Huffman
A system that can learn dictionaries of extraction patterns directly from user-provided examples of texts and events to be extracted from them, and learns patterns that recognize relationships between key constituents based on local syntax.
Using Dependency-Based Features to Take the 'Para-farce' out of Paraphrase
143 Citations2006Stephen Wan, Mark Dras +2 more
A machine learning approach is proposed to be used to filter out inconsistent novel sentences, or False Paraphrases, using the Microsoft Research Paraphrase corpus and investigating whether features based on syntactic dependencies can aid in this task.
…