Saved in:
Bibliographic Details
Main Authors: Gohsen, Marcel, Hagen, Matthias, Potthast, Martin, Stein, Benno
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2403.17564
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916177792466944
author Gohsen, Marcel
Hagen, Matthias
Potthast, Martin
Stein, Benno
author_facet Gohsen, Marcel
Hagen, Matthias
Potthast, Martin
Stein, Benno
contents Since paraphrasing is an ill-defined task, the term "paraphrasing" covers text transformation tasks with different characteristics. Consequently, existing paraphrasing studies have applied quite different (explicit and implicit) criteria as to when a pair of texts is to be considered a paraphrase, all of which amount to postulating a certain level of semantic or lexical similarity. In this paper, we conduct a literature review and propose a taxonomy to organize the 25~identified paraphrasing (sub-)tasks. Using classifiers trained to identify the tasks that a given paraphrasing instance fits, we find that the distributions of task-specific instances in the known paraphrase corpora vary substantially. This means that the use of these corpora, without the respective paraphrase conditions being clearly defined (which is the normal case), must lead to incomparable and misleading results.
format Preprint
id arxiv_https___arxiv_org_abs_2403_17564
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Task-Oriented Paraphrase Analytics
Gohsen, Marcel
Hagen, Matthias
Potthast, Martin
Stein, Benno
Computation and Language
Since paraphrasing is an ill-defined task, the term "paraphrasing" covers text transformation tasks with different characteristics. Consequently, existing paraphrasing studies have applied quite different (explicit and implicit) criteria as to when a pair of texts is to be considered a paraphrase, all of which amount to postulating a certain level of semantic or lexical similarity. In this paper, we conduct a literature review and propose a taxonomy to organize the 25~identified paraphrasing (sub-)tasks. Using classifiers trained to identify the tasks that a given paraphrasing instance fits, we find that the distributions of task-specific instances in the known paraphrase corpora vary substantially. This means that the use of these corpora, without the respective paraphrase conditions being clearly defined (which is the normal case), must lead to incomparable and misleading results.
title Task-Oriented Paraphrase Analytics
topic Computation and Language
url https://arxiv.org/abs/2403.17564