TU Darmstadt / ULB / TUbiblio

Metaphoric Paraphrase Generation

Stowe, Kevin ; Ribeiro, Leonardo F. R. ; Gurevych, Iryna (2020)
Metaphoric Paraphrase Generation.
doi: 10.48550/arXiv.2002.12854
Report, Bibliographie

Kurzbeschreibung (Abstract)

This work describes the task of metaphoric paraphrase generation, in which we are given a literal sentence and are charged with generating a metaphoric paraphrase. We propose two different models for this task: a lexical replacement baseline and a novel sequence to sequence model, 'metaphor masking', that generates free metaphoric paraphrases. We use crowdsourcing to evaluate our results, as well as developing an automatic metric for evaluating metaphoric paraphrases. We show that while the lexical replacement baseline is capable of producing accurate paraphrases, they often lack metaphoricity, while our metaphor masking model excels in generating metaphoric sentences while performing nearly as well with regard to fluency and paraphrase quality.

Typ des Eintrags: Report
Erschienen: 2020
Autor(en): Stowe, Kevin ; Ribeiro, Leonardo F. R. ; Gurevych, Iryna
Art des Eintrags: Bibliographie
Titel: Metaphoric Paraphrase Generation
Sprache: Englisch
Publikationsjahr: 28 Februar 2020
Verlag: arXiv
Titel der Zeitschrift, Zeitung oder Schriftenreihe: Computation and Language
Reihe: Computation and Language
DOI: 10.48550/arXiv.2002.12854
URL / URN: https://arxiv.org/abs/2002.12854
Kurzbeschreibung (Abstract):

This work describes the task of metaphoric paraphrase generation, in which we are given a literal sentence and are charged with generating a metaphoric paraphrase. We propose two different models for this task: a lexical replacement baseline and a novel sequence to sequence model, 'metaphor masking', that generates free metaphoric paraphrases. We use crowdsourcing to evaluate our results, as well as developing an automatic metric for evaluating metaphoric paraphrases. We show that while the lexical replacement baseline is capable of producing accurate paraphrases, they often lack metaphoricity, while our metaphor masking model excels in generating metaphoric sentences while performing nearly as well with regard to fluency and paraphrase quality.

Zusätzliche Informationen:

Preprint

Fachbereich(e)/-gebiet(e): 20 Fachbereich Informatik
20 Fachbereich Informatik > Ubiquitäre Wissensverarbeitung
Hinterlegungsdatum: 15 Sep 2021 13:46
Letzte Änderung: 22 Jul 2024 11:51
PPN:
Export:
Suche nach Titel in: TUfind oder in Google
Frage zum Eintrag Frage zum Eintrag

Optionen (nur für Redakteure)
Redaktionelle Details anzeigen Redaktionelle Details anzeigen