Learning to paraphrase
Published 1 January 2003Open access
Regina Barzilay, Lillian Lee
Citations432
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 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.
Abstract
We address the text-to-text generation problem of sentence-level paraphrasing --- a phenomenon distinct from and more difficult than word- or phrase-level paraphrasing. Our approach 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. The results of our evaluation experiments show that the system derives accurate paraphrases, outperforming baseline systems.
Keywords
Computer Science
BiometricsThe Measurement of Observer Agreement for Categorical Data
78,934 Citations1977J. Richard Landis, Gary G. Koch
A general statistical methodology for the analysis of multivariate categorical data arising from observer reliability studies is presented and tests for interobserver bias are presented in terms of first-order marginal homogeneity and measures of interob server agreement are developed as generalized kappa-type statistics.
Cambridge University Press eBooksBiological Sequence Analysis
3,283 Citations1998Richard Durbin, Sean R. Eddy +2 more
This book gives a unified, up-to-date and self-contained account, with a Bayesian slant, of such methods, and more generally to probabilistic methods of sequence analysis.
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.
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.
Distributional clustering of English words
994 Citations1993Fernando Pereira, Naftali Tishby +1 more
Explorations in Automatic Thesaurus Discovery
757 Citations1994Gregory Grefenstette
The aim of this monograph is to provide a catalog of words and phrases used in ThesaurusGeneration, as well as some examples of other writers' work, which have been used in similar contexts.
Computer Speech & LanguageFinding consensus in speech recognition: word error minimization and other applications of confusion networks
641 Citations2000Lidia Mangu, Eric Brill +1 more
A new framework for distilling information from word lattices is described to improve the accuracy of the speech recognition output and obtain a more perspicuous representation of a set of alternative hypotheses.
Proceedings of the 17th international conference on Computational linguistics -Automatic retrieval and clustering of similar words
550 Citations1998Dekang Lin
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.
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.
Statistics-Based Summarization - Step One: Sentence Compression
405 Citations2000Kevin Knight, Daniel Marcu
This paper focuses on sentence compression, a simpler version of this larger challenge, and aims to achieve two goals simultaneously: the compressions should be grammatical, and they should retain the most important pieces of information.
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.
Knowledge-Based SystemsAutomatic induction of rules for text simplification
147 Citations1997Raman Chandrasekar, Srinivas Bachu
An algorithm and an implementation are described by which generalized rules for simplification are automatically induced from annotated training material using a novel partial parsing technique which combines constituent structure and dependency information.
Syntagmatic and paradigmatic representations of term variation
111 Citations1999Christian Jacquemin
A two-tier model for the description of morphological, syntactic and semantic variations of multi-word terms is presented and is applied to term normalization of French and English corpora in the medical and agricultural domains.
Kluwer international series in engineering and computer scienceLexical Selection and Paraphrase in a Meaning-Text Generation Model
97 Citations1991Lidija Iordanskaja, Richard Kittredge +1 more
A computationally tractable model for language generation based on the Meaning-Text Theory of Mel’cuk et al., in which the lexicon plays a central role is introduced, to illustrate the descriptive scope and paraphrase capabilities of the model.
Columbia Academic Commons (Columbia University)Revision-Based Generation of Natural Language Summaries Providing Historical Background: Corpus-Based Analysis, Design, Implementation and Evaluation
80 Citations1994Jacques Robin
This thesis presents a new generation model in which a first pass builds a draft containing only the essential new facts to report and a second pass incrementally revises this draft to opportunistically add as many background facts as can fit within the space limit.
Bootstrapping lexical choice via multiple-sequence alignment
78 Citations2002Regina Barzilay, Lillian Lee
The method lever-ages latent information contained in multi-parallel corpora --- datasets that supply several verbalizations of the corresponding semantics rather than just one to generate natural language versions of computer-generated mathematical proofs.
Paraphrasing using given and new information in a question-answer system
78 Citations1979Kathleen McKeown
The design and implementation of a paraphrase component for a natural language question-answer system (CO-OP) is presented and a major point made is the role of given and new information in formulating a paraphraser that differs in a meaningful way from the user's question.
Practical issues in automatic documentation generation
69 Citations1994Kathleen McKeown, Karen Kukich +1 more
The user needs analysis performed and how it influenced the development of PLANDoc are described, showing how it pinpointed the need for a sublanguage specification, allowing us to identify input messages and to characterize the different sentence paraphrases for realizing them.
Computational IntelligenceUsing collocations for language generation1
58 Citations1991Frank Smadja, Kathleen McKeown
An implemented generator, Cook, is described, which uses a flexible lexicon containing a range of collocations, from idiomatic phrases to word pairs that were compiled automatically from text corpora using a lexicographic tool, Xtract.
Strategies for effective paraphrasing
45 Citations1988Marie Meteer, Varda Shaked
A new dimension to paraphrasing text in which characteristics of the original text motivate strategies for effective paraphrase is presented, which combines two existing robust components: the IRUS-II natural language understanding system and the SPOKESMAN generation system.
Bootstrapping bilingual data using consensus translation for a multilingual instant messaging system
41 Citations2002Srinivas Bangalore, Vanessa Murdock +1 more
This paper proposes techniques to alleviate the bilingual data bottleneck by creating a consensus from translations of monolingual data provided by several off-the-shelf translation engines, and compute the consensus alignment using a multi-sequence alignment algorithm used for DNA sequence alignment.
Grammar Inference and Statistical Machine Translation
33 Citations2009Ye‐Yi Wang, Jaime Carbonell +1 more
A structure-based alignment model is introduced that can directly depict the structure between English and German spoken languages and results in focused learning of word alignment, therefore it can alleviate the sparse data problem.
Construction of a hierarchical translation memory
13 Citations2000Stephan Vogel, Hermann Ney
A hierarchical translation memory, consisting of a cascade of finite state transducers, is proposed, which is applied to convert sentence pairs from a bilingual corpus into translation patterns, which are then used as a translation memory.