Paraphrase
A paraphrase (/ˈpærəˌfreɪz/) or rephrase is a rewording of a text that retains the original meaning.[1] Paraphrasing can enhance clarity and effectiveness in conveying ideas. It involves expressing the same concepts as the original text in a new way. For example, when someone tells a story they have heard, they paraphrase it in their own words while preserving the meaning.[1] The term comes from the Latin paraphrasis, from Ancient Greek παράφρασις (paráphrasis) 'additional manner of expression'. The act of paraphrasing is also called paraphrasis.
History
[edit]Although paraphrases likely abounded in oral traditions, it dates back to at least Roman times, when Quintilian suggested it as a language exercise for students. This practice continued in the Middle Ages, with figures such as Geoffrey of Vinsauf incorporating paraphrasing into educational exercises to enhance students' language skills. The study of paraphrasing has gained significance due to issues surrounding plagiarism and the importance of original authorship.[2]
Types
[edit]Fred Inglis outlines five levels of paraphrasing for educational purposes:[3][4]
- replacing words with synonyms
- varying sentence structure
- reordering information
- turning long sentences into multiple shorter ones (or vice versa)
- expressing abstract concepts more concretely.
Some believe that using synonyms in paraphrasing can be a helpful learning tool; however, it is important to teach students how to restructure sentences to avoid plagiarism.[5] Research on English language learners has shown that ESL students often rely on synonyms rather than altering sentence structure when paraphrasing. A study involving Vietnamese ESL learners revealed that they preferred using synonyms because they were afraid that changing the sentence structure could alter the meaning. Na and Mai recommend that ESL teachers incorporate diverse activities, including tasks that involve modifying syntax, to help students improve their paraphrasing skills. Additionally, students should be provided with source texts that they can easily comprehend to practice paraphrasing effectively.[6]
Natural Language Processing researchers have identified different (atomic) types of paraphrases to study how humans rephrase text. These paraphrase types can be categorized into six main groups, each representing distinct methods of altering a text to communicate a comparable meaning:[7][8][9][10]
- morphology-based changes
- lexicon-based changes
- lexico-syntactic-based changes
- syntax-based changes
- discourse-based changes
- extremes.
Morphology-based changes involve altering word formation, such as changing verb tenses or noun numbers. For example, changing "walks" to "walked" is a morphological change that adjusts the verb tense. Lexicon-based changes involve substituting words with synonyms or closely related terms without significantly changing the sentence structure. For instance, replacing "quick" with "fast" in a sentence conveys a similar speed attribute. Lexico-syntactic-based changes combine lexical modifications with sentence structure alterations. For instance, transforming an active voice sentence like "The cat chased the mouse" into a passive voice sentence, "The mouse was chased by the cat" involves changing both the sentence structure and some words. Syntax-based changes focus on sentence structure rather than individual words. For example, breaking down a complex sentence into two simpler sentences while retaining the original meaning falls under this category. Discourse-based changes, such as rearranging points in a paragraph or modifying how arguments are presented without changing the factual content, impact the overall text structure. Extreme changes involve significant alterations to the text, potentially introducing new information or omitting essential details, thereby stretching the boundaries of conventional paraphrasing.
Machine learning models have been developed to generate paraphrases with specific characteristics, such as high semantic similarity and diverse syntax.[11][12] These models have various applications, such as aiding language learners by providing simplified paraphrases that highlight linguistic variations such as syntax. Universities can utilize these models to analyze students' assignments and detect content similarity for plagiarism detection.[13][14][15] Additionally, different types of paraphrases, such as syntax and lexicon changes, are used for prompt engineering to enhance model performance by adjusting prompts in specific linguistic aspects.[16][17][18]
Analysis
[edit]A paraphrase is a restatement of a text that aims to clarify or explain its meaning.[19] For instance, if the original text says, "The signal was red", it may be paraphrased as "The train was not allowed to pass as the red signal light was illuminated". A paraphrase can be introduced with verbum dicendi, a declaratory expression that signals the transition to the paraphrase. For example, in "The author states 'The signal was red', that is, the train was not allowed to proceed," the that is signals the paraphrase that follows.
A paraphrase does not need to accompany a direct quotation.[20] The paraphrase typically serves to put the source's statement into perspective or to clarify the context in which it appeared.[21] A paraphrase is typically more detailed than a summary.[22] The source should be added at the end of the sentence: When the light was red, trains could not go (Wikipedia). A paraphrase may attempt to preserve the essential meaning of the material being paraphrased.[23][24] Thus, the (intentional or otherwise) reinterpretation of a source to infer a meaning that is not explicitly evident in the source itself qualifies as "original research," and not a paraphrase. Unlike a metaphrase, which represents a "formal equivalent" of the source, a paraphrase represents a "dynamic equivalent" thereof. While a metaphrase attempts to literally translate a text, a paraphrase conveys the essential thought expressed in a source text—if necessary, at the expense of literality. For details, see dynamic and formal equivalence.
In your own words
[edit]The term "in your own words" is commonly used to indicate that the writer has rephrased the text in their unique writing style—how they would have expressed the idea if they had created it.[25] Presently, models exist for understanding and identifying paraphrases in natural language texts.[26] Additionally, sentences can be paraphrased automatically using text simplification software.[27]
N'Ko
[edit]N’Ko "uses a set of paired punctuation, U+2E1C ⸜ LEFT LOW PARAPHRASE BRACKET and U+2E1D ⸝ RIGHT LOW PARAPHRASE BRACKET, to indicate indirect quotations."[28]
See also
[edit]References
[edit]- ^ a b Stewart, Donald (1971). "Metaphor and Paraphrase". Philosophy & Rhetoric. 4 (2): 111–123. ISSN 0031-8213. JSTOR 40236756.
- ^ D'Angelo (October 1979). "The Art of Paraphrase". College Composition and Communication. 30 (3): 255–259. doi:10.2307/356389. JSTOR 356389.
- ^ Skills for Academic and Career Success. Pearson Higher Education AU. 16 September 2013. p. 104. ISBN 9781486014712.
- ^ Inglis, Fred (2008). Key Concepts in Education. SAGE Publications. ISBN 9780857022998.
- ^ Ruiter, Rik (2005). Highway to E.S.L. iUniverse. ISBN 9780595342211.
- ^ Chi Do Na; Nguyen Xuan Nhat Chi Mai (2017). "Paraphrasing in Academic Writing: a Case Study of Vietnamese Learners of English" (PDF). Language Education in Asia.
- ^ Kovatchev, Venelin; Martí, M. Antònia; Salamó, Maria (2018). Calzolari, Nicoletta; Choukri, Khalid; Cieri, Christopher; Declerck, Thierry; Goggi, Sara; Hasida, Koiti; Isahara, Hitoshi; Maegaard, Bente; Mariani, Joseph (eds.). "ETPC - A Paraphrase Identification Corpus Annotated with Extended Paraphrase Typology and Negation". Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018). Miyazaki, Japan: European Language Resources Association (ELRA).
- ^ Levin, Beth (1993). English Verb Classes and Alternations: A Preliminary Investigation. University of Chicago Press. ISBN 978-0-226-47533-2.
- ^ Milicevic, Jasmina (2011-11-10). La paraphrase (in French). ISBN 978-3-0352-0096-6.
- ^ Vila, Marta; Bertran, Manuel; Martí, M. Antònia; Rodríguez, Horacio (2015-03-01). "Corpus annotation with paraphrase types: new annotation scheme and inter-annotator agreement measures". Language Resources and Evaluation. 49 (1): 77–105. doi:10.1007/s10579-014-9272-5. ISSN 1574-0218. S2CID 254370726.
- ^ Bandel, Elron; Aharonov, Ranit; Shmueli-Scheuer, Michal; Shnayderman, Ilya; Slonim, Noam; Ein-Dor, Liat (2022). Muresan, Smaranda; Nakov, Preslav; Villavicencio, Aline (eds.). "Quality Controlled Paraphrase Generation". Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Dublin, Ireland: Association for Computational Linguistics: 596–609. arXiv:2203.10940. doi:10.18653/v1/2022.acl-long.45.
- ^ Wahle, Jan Philip; Gipp, Bela; Ruas, Terry (2023). "Paraphrase Types for Generation and Detection". In Bouamor, Houda; Pino, Juan; Bali, Kalika (eds.). Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. Singapore: Association for Computational Linguistics. pp. 12148–12164. doi:10.18653/v1/2023.emnlp-main.746.
- ^ Wahle, Jan Philip; Ruas, Terry; Meuschke, Norman; Gipp, Bela (2021). Are Neural Language Models Good Plagiarists? A Benchmark for Neural Paraphrase Detection. pp. 226–229. arXiv:2103.12450. doi:10.1109/JCDL52503.2021.00065. ISBN 978-1-6654-1770-9.
- ^ Wahle, Jan Philip; Ruas, Terry; Kirstein, Frederic; Gipp, Bela (2022). "How Large Language Models are Transforming Machine-Paraphrase Plagiarism". In Goldberg, Yoav; Kozareva, Zornitsa; Zhang, Yue (eds.). Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing. Abu Dhabi, United Arab Emirates: Association for Computational Linguistics. pp. 952–963. doi:10.18653/v1/2022.emnlp-main.62.
- ^ Hunt, Ethan; Janamsetty, Ritvik; Kinares, Chanana; Koh, Chanel; Sanchez, Alexis; Zhan, Felix; Ozdemir, Murat; Waseem, Shabnam; Yolcu, Osman; Dahal, Binay; Zhan, Justin; Gewali, Laxmi; Oh, Paul (2019). Machine Learning Models for Paraphrase Identification and its Applications on Plagiarism Detection. pp. 97–104. doi:10.1109/ICBK.2019.00021. ISBN 978-1-7281-4607-2.
- ^ Leidinger, Alina; van Rooij, Robert; Shutova, Ekaterina (2023). "The language of prompting: What linguistic properties make a prompt successful?". Association for Computational Linguistics: 9210–9232. arXiv:2311.01967. doi:10.18653/v1/2023.findings-emnlp.618.
- ^ Wahle, Jan Philip; Ruas, Terry; Xu, Yang; Gipp, Bela (2024). "Paraphrase Types Elicit Prompt Engineering Capabilities". In Al-Onaizan, Yaser; Bansal, Mohit; Chen, Yun-Nung (eds.). Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. Miami, Florida, USA: Association for Computational Linguistics. pp. 11004–11033. arXiv:2406.19898. doi:10.18653/v1/2024.emnlp-main.617.
- ^ Linzbach, Stephan; Dimitrov, Dimitar; Kallmeyer, Laura; Evang, Kilian; Jabeen, Hajira; Dietze, Stefan (2024). "Dissecting Paraphrases: The Impact of Prompt Syntax and supplementary Information on Knowledge Retrieval from Pretrained Language Models". In Duh, Kevin; Gomez, Helena; Bethard, Steven (eds.). Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). Mexico City, Mexico: Association for Computational Linguistics. pp. 3645–3655. arXiv:2404.01992. doi:10.18653/v1/2024.naacl-long.201.
- ^ Fenceroy, Edna (2011-11-01). Minimizing Conflict Through Restorative Conferencing: Changing Lives Through Changing Attitudes. WestBow Press. p. 93. ISBN 978-1-4497-2243-2.
- ^ Lohumi, Shama; Lohumi, Rakesh (2021-09-22). Communicative English for Nurses , 3rd Edition - E-Book. Elsevier Health Sciences. ISBN 978-81-312-6376-1.
- ^ Ganguly, Amit (2018-07-11). English Communication: E-Book. SBPD Publications. p. 72. ISBN 978-93-5167-673-7.
- ^ "Decide when to Quote, Paraphrase and Summarize - University of Houston-Victoria". www.uhv.edu. Retrieved 2024-10-14.
- ^ Lohumi, Shama; Lohumi, Rakesh (2021-09-22). Communicative English for Nurses , 3rd Edition - E-Book. Elsevier Health Sciences. ISBN 978-81-312-6376-1.
- ^ "QuillBot Premium". lucidgen.com. 2021-10-26. Retrieved 2024-10-14.
- ^ "Writing in your own words". The Open University. Retrieved July 27, 2012.
- ^ Figueroa, Alejandro; Guenter Neumann (2013). Learning to Rank Effective Paraphrases from Query Logs for Community Question Answering. AAAI.
- ^ Shardlow, Matthew. "A survey of automated text simplification." International Journal of Advanced Computer Science and Applications 4.1 (2014): 58–70.
- ^ The Unicode Core Spec, "N'Ko" § "Punctuation" https://www.unicode.org/versions/Unicode17.0.0/core-spec/chapter-19/#G18895