Strategies for effective paraphrasing

Meteer, Marie; Shaked, Varda

doi:10.3115/991719.991724

Cited by 32 publications

(21 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Paraphrase Generation Paraphrases express the same content with alternative surface forms. Their automatic generation has been studied for decades: rule-based (McKeown, 1980;Meteer and Shaked, 1988) and data-driven methods (Madnani and J. Dorr, 2010) have been explored. Data-driven approaches have considered different source of training data, including multiple translations of the same text (Barzilay and McKeown, 2001;Pang et al, 2003) or alignments of comparable corpora, such as news from the same period (Dolan et al, 2004;Barzilay and Lee, 2003).…”

Section: Related Workmentioning

confidence: 99%

Unsupervised Paraphrasing without Translation

Roy¹,

Grangier²

2019

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

View full text Add to dashboard Cite

Paraphrasing exemplifies the ability to abstract semantic content from surface forms. Recent work on automatic paraphrasing is dominated by methods leveraging Machine Translation (MT) as an intermediate step. This contrasts with humans, who can paraphrase without being bilingual. This work proposes to learn paraphrasing models from an unlabeled monolingual corpus only. To that end, we propose a residual variant of vector-quantized variational auto-encoder. We compare with MT-based approaches on paraphrase identification, generation, and training augmentation. Monolingual paraphrasing outperforms unsupervised translation in all settings. Comparisons with supervised translation are more mixed: monolingual paraphrasing is interesting for identification and augmentation; supervised translation is superior for generation.

show abstract

Section: Related Workmentioning

confidence: 99%

Unsupervised Paraphrasing without Translation

Roy¹,

Grangier²

2019

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

View full text Add to dashboard Cite

show abstract

“…Among them,McKeown(McKeown 1983)designed and implemented a paraphraser of questions by users in the Q-and-A system CO-OP,to ensure that the system would correctly understand its users. Meteer and Shaked(Meteer and Shaked 1988)discussed paraphrasing strategies for displaying several ambiguities of inputs by users in an interactive dialog system. It is important to reduce the burden of transfer to realize multilingual MT.In this sense,…”

Section: Related Workmentioning

confidence: 99%

Interaction between Paraphraser and Transfer for Spoken Language Translation

Yamamoto

2004

Journal of Natural Language Processing

View full text Add to dashboard Cite

One of the problems in spoken language translation is the enormous variety of expressions not found in text translation.This volume can lead to a sparse translation coverage.In order to tackle this problem,we propose a machine translation model where an input is translated through both source-language and target-language paraphrasing processes.In this paper,we discuss the source paraphrasing and the language transfer processes,and the design of our translation model.In the source language paraphrasing,we take the practical approach of untangling slight variations in the source language before transferring a source expression to its target.We discuss how effective our paraphrasing process is in the sense of reducing varieties in a spoken language,with a focus on how many source language patterns are reduced by paraphrasing.In the translation model,we propose an interaction model between the source language paraphraser and the transfer,unlike the conventional assembly-line process flow.In our evaluation we illustrate that over 70% of the input utterances is expected to somehow be changed.Accordingly,we can achieve that one-fifth of all skeleton expressions can be merged into other skeletons, that increases chances of correct translations being obtained.Furthermore,we observe that our interaction model with the paraphraser increases 20-40 percentage points of translation capability,regardless of the transfer knowledge size.

show abstract

“…Although some approaches have been proposed for solving specific problems, such as generating ellipsis (e.g., Jameson & Wahlster, 1982); generation of paraphrases (e.g., Meteer & Shaked, 1988;Neumann, 1994); generation of referential expressions (Dale, 1990); or incremental generation (e.g., DeSmedt & Kempen, 1987), there exists currently no theoretical and practical framework, which could serve as a platform for combining all these specific operational issues.…”

Section: Future Directionsmentioning

confidence: 99%